Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > sci.physics.relativity > #671581 > unrolled thread

The Wuhan Virus that destroyed Python [ggml Manifesto]

Started byMild Shock <janburse@fastmail.fm>
First post2026-07-22 21:00 +0200
Last post2026-09-22 18:05 +0200
Articles 20 on this page of 173 — 18 participants

Back to article view | Back to sci.physics.relativity


Contents

  The Wuhan Virus that destroyed Python [ggml Manifesto] Mild Shock <janburse@fastmail.fm> - 2026-07-22 21:00 +0200
    Deadlock Exorcism: Switch from Push to Pull [A pi-calculus Specification of Prolog] (Re: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-07-23 00:23 +0200
      Why do you even need a mpmc queue? [Thunder Kittens] (Re: Deadlock Exorcism: Switch from Push to Pull) Mild Shock <janburse@fastmail.fm> - 2026-07-23 08:43 +0200
        Trivial balancing example for (int i=0; i<global_id; i++) (Re: Why do you even need a mpmc queue? [Thunder Kittens]) Mild Shock <janburse@fastmail.fm> - 2026-07-23 08:57 +0200
          Enqueue/dequeue need not be fast and can spinn ["fairness" questions] (Was: Trivial balancing example for (int i=0; i<global_id; i++)) Mild Shock <janburse@fastmail.fm> - 2026-07-23 09:11 +0200
            The Pixel Phone AI Experiment Song (Re: Enqueue/dequeue need not be fast and can spinn ["fairness" questions] ) Mild Shock <janburse@fastmail.fm> - 2026-07-23 09:21 +0200
        Re: Why do you even need a mpmc queue? [Thunder Kittens] (Re: Deadlock Exorcism: Switch from Push to Pull) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-23 08:24 -0700
    Potential Python Recovery: Free Threading [3.13 release] (Was: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-07-23 10:19 +0200
      Re: Potential Python Recovery: Free Threading [3.13 release] (Was: The Wuhan Virus that destroyed Python [ggml Manifesto]) Ross Valikhanov <kavna@rl.ru> - 2026-07-23 16:01 +0000
    Re: The Wuhan Virus that destroyed Python [ggml Manifesto] Ramon Dubenkov <omd@nnk.ru> - 2026-07-23 13:38 +0000
    The things XILINX braught to the AMD table (Was: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-07-23 18:47 +0200
      NIVIDIA evacuated its Chinese market [Tau Scaling] (Was: The things XILINX braught to the AMD table) Mild Shock <janburse@fastmail.fm> - 2026-07-23 19:11 +0200
      NVIDIA evacuated its Chinese market [Tau Scaling] (Re: The things XILINX braught to the AMD table) Mild Shock <janburse@fastmail.fm> - 2026-07-23 19:12 +0200
        Re: NVIDIA evacuated its Chinese market [Tau Scaling] (Re: The things XILINX braught to the AMD table) Lane W <cactus_DAC@yahoo.com> - 2026-07-23 11:22 -0600
          Micro penis mother sung arias (Was: NVIDIA evacuated its Chinese market [Tau Scaling]) Mild Shock <janburse@fastmail.fm> - 2026-07-24 14:38 +0200
            Re: Micro penis mother sung arias (Was: NVIDIA evacuated its Chinese market [Tau Scaling]) Lane W <cactus_DAC@yahoo.com> - 2026-07-24 07:15 -0600
              Micro penis brain is in constant hiatus (Was: Micro penis mother sung arias) Mild Shock <janburse@fastmail.fm> - 2026-07-24 15:24 +0200
                Re: Micro penis brain is in constant hiatus (Was: Micro penis mother sung arias) Mild Shock <janburse@fastmail.fm> - 2026-07-24 15:36 +0200
                Ignoramus or Ignorabimus: I don't care (π-WAM) (Re: Micro penis brain is in constant hiatus) Mild Shock <janburse@fastmail.fm> - 2026-07-24 15:38 +0200
                  Re: Ignoramus or Ignorabimus: I don't care (π-WAM) (Re: Micro penis brain is in constant hiatus) Lane W <cactus_DAC@yahoo.com> - 2026-07-24 08:31 -0600
                    You are a moron, brainless putin payed (Was: Ignoramus or Ignorabimus: I don't care (π-WAM)) Mild Shock <janburse@fastmail.fm> - 2026-07-24 18:01 +0200
                      Re: You are a moron, brainless putin payed (Was: Ignoramus or Ignorabimus: I don't care (π-WAM)) Lane W <cactus_DAC@yahoo.com> - 2026-07-24 10:27 -0600
                        Yeah keep reading my posts, uninspired fool (Was: You are a moron, brainless putin payed) Mild Shock <janburse@fastmail.fm> - 2026-07-24 19:45 +0200
                          Re: Yeah keep reading my posts, uninspired fool (Was: You are a moron, brainless putin payed) Lane W <cactus_DAC@yahoo.com> - 2026-07-24 12:11 -0600
                            LoL (Was: Yeah keep reading my posts, uninspired fool ) Mild Shock <janburse@fastmail.fm> - 2026-07-24 20:12 +0200
                              Re: LoL (Was: Yeah keep reading my posts, uninspired fool ) Lane W <cactus_DAC@yahoo.com> - 2026-07-24 12:53 -0600
                  Out of the blue accusation span 15 days [Empirical USENET study] (Was: Ignoramus or Ignorabimus: I don't care (π-WAM)) Mild Shock <janburse@fastmail.fm> - 2026-07-24 20:26 +0200
                  A brain desease of 20 days [Rossy Boy] (Re: Ignoramus or Ignorabimus: I don't care (π-WAM)) Mild Shock <janburse@fastmail.fm> - 2026-07-29 18:40 +0200
                    Re: A brain desease of 20 days [Rossy Boy] (Re: Ignoramus or Ignorabimus: I don't care (π-WAM)) Mantra Mahonov <hnaam@aat.ru> - 2026-07-29 21:15 +0000
                      I didn't use a Ryzen Halo, whats wrong with you? (Was: A brain desease of 20 days [Rossy Boy]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 23:24 +0200
                    Ignoramus / Ignorabimus Barometer: Almost 1 Month (Was: A brain desease of 20 days [Rossy Boy]) Mild Shock <janburse@fastmail.fm> - 2026-08-03 00:06 +0200
                      Re: Ignoramus / Ignorabimus Barometer: Almost 1 Month (Was: A brain desease of 20 days [Rossy Boy]) Lane W <cactus_DAC@yahoo.com> - 2026-08-03 13:16 -0600
                        Re: Ignoramus / Ignorabimus Barometer: Almost 1 Month (Was: A brain desease of 20 days [Rossy Boy]) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2026-08-03 12:54 -0700
                          No you didn't try, you only spammed old code (Was: Ignoramus / Ignorabimus Barometer: Almost 1 Month) Mild Shock <janburse@fastmail.fm> - 2026-08-03 22:15 +0200
                    Food for thought: Bayesian Experimental Designer (Was: A brain desease of 20 days [Rossy Boy]) Mild Shock <janburse@fastmail.fm> - 2026-09-24 15:47 +0200
        ASML stocks are plunging, bye bye dutchies (Was: NVIDIA evacuated its Chinese market [Tau Scaling]) Mild Shock <janburse@fastmail.fm> - 2026-07-28 14:17 +0200
    Little Data Center on Your Palm [AI Laptops for 500 USD] (Was: The Wuhan Virus that destroyed Python [ggml Manifesto] Mild Shock <janburse@fastmail.fm> - 2026-07-24 17:58 +0200
      2008: 4 Blades + Tesla S1070 versus 2026: 1 AI Laptop (Re: Little Data Center on Your Palm [AI Laptops for 500 USD]) Mild Shock <janburse@fastmail.fm> - 2026-07-24 18:16 +0200
      Re: Little Data Center on Your Palm [AI Laptops for 500 USD] (Was: The Wuhan Virus that destroyed Python [ggml Manifesto] Bradford Babkoff <ffb@odbb.ru> - 2026-07-24 18:05 +0000
        LoL (Was: Little Data Center on Your Palm [AI Laptops for 500 USD]) Mild Shock <janburse@fastmail.fm> - 2026-07-24 20:11 +0200
      Budget AI Laptop 2026 versus Cray T3D 1995 (Re: Little Data Center on Your Palm [AI Laptops for 500 USD]) Mild Shock <janburse@fastmail.fm> - 2026-08-05 14:23 +0200
        Re: Budget AI Laptop 2026 versus Cray T3D 1995 (Re: Little Data Center on Your Palm [AI Laptops for 500 USD]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-05 13:16 -0700
    Hurry the blue bus doesnt stop indefinitely (Was: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-07-24 20:36 +0200
      Not SIMD, a MIMD design for NVIDIA Volta (Re: Hurry the blue bus doesnt stop indefinitely) Mild Shock <janburse@fastmail.fm> - 2026-07-24 20:57 +0200
        Could take 3-4 months find machine / browser (Was Not SIMD, a MIMD design for NVIDIA Volta) Mild Shock <janburse@fastmail.fm> - 2026-07-24 21:15 +0200
        The Koan of pi-WAM queues [FORTRAN-S] (Was: Not SIMD, a MIMD design for NVIDIA Volta) Mild Shock <janburse@fastmail.fm> - 2026-07-26 19:52 +0200
          The turbo capping of AI Laptops (Re: The Koan of pi-WAM queues [FORTRAN-S]) Mild Shock <janburse@fastmail.fm> - 2026-07-26 20:01 +0200
          Re: The Koan of pi-WAM queues [FORTRAN-S] (Was: Not SIMD, a MIMD design for NVIDIA Volta) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-26 20:33 -0700
            Why forget Bulgarians, never on my mind (Re: The Koan of pi-WAM queues [FORTRAN-S] (Was: Not SIMD, a MIMD design for NVIDIA Volta) Mild Shock <janburse@fastmail.fm> - 2026-07-27 09:14 +0200
              miniTriton CUDA is an alternative to torch variants (Was: Why forget Bulgarians, never on my mind) Mild Shock <janburse@fastmail.fm> - 2026-07-27 09:40 +0200
                Andrej Karpathy original gangster of Budget Laptop (Was: miniTriton CUDA is an alternative to torch variants) Mild Shock <janburse@fastmail.fm> - 2026-07-27 09:51 +0200
                  Re: Andrej Karpathy original gangster of Budget Laptop (Was: miniTriton CUDA is an alternative to torch variants) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-27 01:41 -0700
              Re: Why forget Bulgarians, never on my mind (Re: The Koan of pi-WAM queues [FORTRAN-S] (Was: Not SIMD, a MIMD design for NVIDIA Volta) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-27 01:38 -0700
              The evolution of hardware and GPT-2 training (Was: Why forget Bulgarians, never on my mind) Mild Shock <janburse@fastmail.fm> - 2026-07-27 10:56 +0200
                How speed up π-WAM with vector operations (Was: The evolution of hardware and GPT-2 training) Mild Shock <janburse@fastmail.fm> - 2026-07-27 11:08 +0200
                  AI accelerator extend from GPU to CPU [Zero Copying] (Was: How speed up π-WAM with vector operations) Mild Shock <janburse@fastmail.fm> - 2026-07-27 11:21 +0200
                    The invention of vector and matrix registers [NVIDIA Volta] (Was: AI accelerator extend from GPU to CPU [Zero Copying]) Mild Shock <janburse@fastmail.fm> - 2026-07-27 13:20 +0200
                      Maybe they should have named it NVIDIA Einstein [Rossy Boy Toe Sucking] (Re: The invention of vector and matrix registers [NVIDIA Volta] (Was: AI accelerator extend from GPU to CPU [Zero Copying]) Mild Shock <janburse@fastmail.fm> - 2026-07-27 17:14 +0200
                      π-WAM is not adding decimals, it is removing decimals (Re: The invention of vector and matrix registers [NVIDIA Volta]) Mild Shock <janburse@fastmail.fm> - 2026-07-27 18:36 +0200
                        In Budget Laptops the TOPS come with low energy footprint (Was: π-WAM is not adding decimals, it is removing decimals) Mild Shock <janburse@fastmail.fm> - 2026-07-27 18:44 +0200
          Java picky concerning JIT-ing [Luckier with C++/C or FORTRAN compilers?] (Re: The Koan of pi-WAM queues [FORTRAN-S]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 12:55 +0200
      Potato Computer owner impressed by Ukraine Tech [Rossy Boys Brother?] (Re: Hurry the blue bus doesnt stop indefinitely) Mild Shock <janburse@fastmail.fm> - 2026-07-27 16:57 +0200
      The Paul Armer Square Revisited (Was: "Mathematics in the Age of AI") Mild Shock <janburse@fastmail.fm> - 2026-08-19 23:51 +0200
        Communism will Save Us! [Pivot Russia for China] (Re: The Paul Armer Square Revisited) Mild Shock <janburse@fastmail.fm> - 2026-08-20 13:18 +0200
          How to increase your "Convincingness" [Anthropic AI Text Hacked] (Re: Communism will Save Us! [Pivot Russia for China]) Mild Shock <janburse@fastmail.fm> - 2026-08-20 19:35 +0200
            Free Speech for (my) Robots [Kristallnaach BAP] (Re: How to increase your "Convincingness" [Anthropic AI Text Hacked]) Mild Shock <janburse@fastmail.fm> - 2026-08-20 19:48 +0200
              Re: Free Speech for (my) Robots [Kristallnaach BAP] (Re: How to increase your "Convincingness" [Anthropic AI Text Hacked]) Lane W <cactus_DAC@yahoo.com> - 2026-08-20 11:52 -0600
      The Bazar is dead, long live the Bazar [Swarm AI] (Re: Hurry the blue bus doesnt stop indefinitely) Mild Shock <janburse@fastmail.fm> - 2026-09-21 11:30 +0200
        Re: The Bazar is dead, long live the Bazar [Swarm AI] (Re: Hurry the blue bus doesnt stop indefinitely) Lopaz Talagaev <alz@alv.ru> - 2026-09-21 17:29 +0000
        New! P(tao) versus the Euler Turbine [Navier Stokes] (Re: The Bazar is dead, long live the Bazar) Mild Shock <janburse@fastmail.fm> - 2026-09-22 08:42 +0200
          Pontifex Codex the idea of "right and natural" (Re: New! P(tao) versus the Euler Turbine [Navier Stokes]) Mild Shock <janburse@fastmail.fm> - 2026-09-22 09:27 +0200
    Got it. Or are you too stupid? [New Usenet Mantra] (Re: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-07-27 19:00 +0200
      Re: Got it. Or are you too stupid? [New Usenet Mantra] (Re: The Wuhan Virus that destroyed Python [ggml Manifesto]) Kim Baitchorov <bvhkoc@bmc.ru> - 2026-07-27 22:38 +0000
        Clueless about MIMD as usual [Flynn's Taxonomy] (Was: Rossy Boy is neither Einstein nor Zweistein) Mild Shock <janburse@fastmail.fm> - 2026-07-28 11:29 +0200
          confused rossy boy is confused (Re: Clueless about MIMD as usual [Flynn's Taxonomy]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 11:20 +0200
            Gemini, DeepSeek, OpenAI more clever than rossy boy (Re: confused rossy boy is confused) Mild Shock <janburse@fastmail.fm> - 2026-07-29 11:21 +0200
              In AI Acceleration nobody cares about CivetWeb (Re: Gemini, DeepSeek, OpenAI more clever than rossy boy) Mild Shock <janburse@fastmail.fm> - 2026-07-29 11:29 +0200
                Run with minimum HTTPS and .mjs type (Re: In AI Acceleration nobody cares about CivetWeb) Mild Shock <janburse@fastmail.fm> - 2026-07-29 11:49 +0200
                  Your strictness is your problem , not mine [See WebLLM] (Re: Run with minimum HTTPS and .mjs type) Mild Shock <janburse@fastmail.fm> - 2026-07-29 11:51 +0200
                Re: In AI Acceleration nobody cares about CivetWeb (Re: Gemini, DeepSeek, OpenAI more clever than rossy boy) Lane W <cactus_DAC@yahoo.com> - 2026-07-29 07:06 -0600
                Re: In AI Acceleration nobody cares about CivetWeb (Re: Gemini, DeepSeek, OpenAI more clever than rossy boy) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-29 07:20 -0700
          You are still chewing on SIMD. LoL (Re: Clueless about MIMD as usual [Flynn's Taxonomy]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 17:14 +0200
            Hurry Rossy Boy, the blue bus is waiting (Re: You are still chewing on SIMD. LoL) Mild Shock <janburse@fastmail.fm> - 2026-07-29 17:54 +0200
              Look how they advertized CUDA and logical threads (Re: Hurry Rossy Boy, the blue bus is waiting) Mild Shock <janburse@fastmail.fm> - 2026-07-29 17:56 +0200
                Forget any arithmetization of product FSA (Re: Look how they advertized CUDA and logical threads) Mild Shock <janburse@fastmail.fm> - 2026-07-29 17:57 +0200
            Re: You are still chewing on SIMD. LoL (Re: Clueless about MIMD as usual [Flynn's Taxonomy]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-29 10:48 -0700
              Rossy Boys tears could cool a data center [pi-WAM Interleaved Synchronized Emulator] (Was: You are still chewing on SIMD. LoL) Mild Shock <janburse@fastmail.fm> - 2026-07-29 20:03 +0200
                I don't use Rust, you are crazy [Jump off a bridge, idiot] (Re: Rossy Boys tears could cool a data center [pi-WAM Interleaved Synchronized Emulator]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 20:24 +0200
                  Re: I don't use Rust, you are crazy [Jump off a bridge, idiot] (Re: Rossy Boys tears could cool a data center [pi-WAM Interleaved Synchronized Emulator]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-29 12:27 -0700
                    Re: I don't use Rust, you are crazy [Jump off a bridge, idiot] (Re: Rossy Boys tears could cool a data center [pi-WAM Interleaved Synchronized Emulator]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-07-29 13:40 -0700
                      Re: I don't use Rust, you are crazy [Jump off a bridge, idiot] (Re: Rossy Boys tears could cool a data center [pi-WAM Interleaved Synchronized Emulator]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-03 17:05 -0700
                        Do a YouTube video about it (Was: I don't use Rust, you are crazy) Mild Shock <janburse@fastmail.fm> - 2026-08-04 03:00 +0200
                          Standing on the shoulders of giants (Was: Do a YouTube video about it) Mild Shock <janburse@fastmail.fm> - 2026-08-04 03:16 +0200
                            Re: Standing on the shoulders of giants (Was: Do a YouTube video about it) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-04 06:10 -0700
                              You Thief! Stealing Szemeredi, Aristotle, Leibniz, etc.. (Re: Standing on the shoulders of giants) Mild Shock <janburse@fastmail.fm> - 2026-08-04 15:16 +0200
                                Re: You Thief! Stealing Szemeredi, Aristotle, Leibniz, etc.. (Re: Standing on the shoulders of giants) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-04 06:32 -0700
                                  How Rossy Boys plagiarism works [Copy Paste Slop] (Was: You Thief! Stealing Szemeredi, Aristotle, Leibniz, etc..) Mild Shock <janburse@fastmail.fm> - 2026-08-04 17:54 +0200
                                    tatistics gave up, no salient truth [Signal Collapse] (Re: How Rossy Boys plagiarism works [Copy Paste Slop]) Mild Shock <janburse@fastmail.fm> - 2026-08-04 18:21 +0200
                                    Statistics gave up, no salient truth [Signal Collapse] (Was: How Rossy Boys plagiarism works [Copy Paste Slop]) Mild Shock <janburse@fastmail.fm> - 2026-08-04 18:23 +0200
                                      Re: Statistics gave up, no salient truth [Signal Collapse] (Was: How Rossy Boys plagiarism works [Copy Paste Slop]) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-04 20:13 -0700
                                        Re: Statistics gave up, no salient truth [Signal Collapse] (Was: How Rossy Boys plagiarism works [Copy Paste Slop]) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2026-08-05 13:08 -0700
                Hack ecosystem ignorance paired with paranoia [Nand to Tetris] (Re: Rossy Boys tears could cool a data center) Mild Shock <janburse@fastmail.fm> - 2026-07-29 22:51 +0200
                  A funny Q16.16 experiment with Hack (Re: Hack ecosystem ignorance paired with paranoia [Nand to Tetris]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 23:12 +0200
                    Re: A funny Q16.16 experiment with Hack (Re: Hack ecosystem ignorance paired with paranoia [Nand to Tetris]) Alexey Bessonov <nexes@ebxsvs.ru> - 2026-07-29 21:24 +0000
                    Summer Challenge: libSQL = Prolog+Modes [VDBE versus π-WAM] (Re: A funny Q16.16 experiment with Hack) Mild Shock <janburse@fastmail.fm> - 2026-07-30 11:26 +0200
                  I wrote Hack VM for π-WAM from scratch [4 Months total JavaScript, Python and Java] (Re: Hack ecosystem ignorance paired with paranoia [Nand to Tetris]) Mild Shock <janburse@fastmail.fm> - 2026-07-30 19:35 +0200
                    Re: I wrote Hack VM for π-WAM from scratch [4 Months total JavaScript, Python and Java] (Re: Hack ecosystem ignorance paired with paranoia [Nand to Tetris]) Mild Shock <janburse@fastmail.fm> - 2026-07-30 19:49 +0200
                    For WebGPU I first had SIMD in mind (Re: I wrote Hack VM for π-WAM from scratch) Mild Shock <janburse@fastmail.fm> - 2026-07-30 19:50 +0200
                      Corr.: 4 Months --> 4 Weeks (Re: For WebGPU I first had SIMD in mind) Mild Shock <janburse@fastmail.fm> - 2026-07-30 20:05 +0200
                    MIPS is a big Huffman mess [But Hack could do it] (Re: I wrote Hack VM for π-WAM from scratch) Mild Shock <janburse@fastmail.fm> - 2026-07-30 22:30 +0200
                      Not declarative with PHI (Φ) nodes (Re: MIPS is a big Huffman mess [But Hack could do it]) Mild Shock <janburse@fastmail.fm> - 2026-07-30 22:42 +0200
                    Quo Vadis: Extend investigations to WebNN (Re: I wrote Hack VM for π-WAM from scratch) Mild Shock <janburse@fastmail.fm> - 2026-07-31 20:45 +0200
                      Re: Quo Vadis: Extend investigations to WebNN (Re: I wrote Hack VM for π-WAM from scratch) Jereb Pohlebaev <obje@bbvoeoaa.ru> - 2026-07-31 20:23 +0000
                Is Bill Gates right that we will loose jobs [Talkie x Claw] (Re: Rossy Boys tears could cool a data center) Mild Shock <janburse@fastmail.fm> - 2026-09-03 23:41 +0200
                  The Flagging of Students for not Thinking [Elixir Evolution] (Re: Is Bill Gates right that we will loose jobs [Talkie x Claw]) Mild Shock <janburse@fastmail.fm> - 2026-09-04 11:48 +0200
                    Rust Eggs for Statechart Proof Certificates? (Re: The Flagging of Students for not Thinking [Elixir Evolution]) Mild Shock <janburse@fastmail.fm> - 2026-09-05 14:18 +0200
                      Axiom of Determinacy as SCXML × SCXML [AI Chatbot Help] (Re: Rust Eggs for Statechart Proof Certificates? (Re: The Flagging of Students for not Thinking [Elixir Evolution])) Mild Shock <janburse@fastmail.fm> - 2026-09-05 16:26 +0200
    Lamas in a cradle and Lamas on the edge [Red Pyjama] (Was: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 13:02 +0200
      AI Accelerators and ISO Prolog multi-threading (Was: Lamas in a cradle and Lamas on the edge [Red Pyjama]) Mild Shock <janburse@fastmail.fm> - 2026-07-29 17:01 +0200
        Actor/Erlang is dead, no Thread and Mailbox conflation [golang channels] (Was: AI Accelerators and ISO Prolog multi-threading) Mild Shock <janburse@fastmail.fm> - 2026-07-29 17:05 +0200
          Can library(ironpaw) repurpose FFT hardware [Glimps into Ryzen AI 7 350] (Was: Actor/Erlang is dead, no Thread and Mailbox conflation) Mild Shock <janburse@fastmail.fm> - 2026-08-01 02:29 +0200
            Re: Can library(ironpaw) repurpose FFT hardware [Glimps into Ryzen AI 7 350] Thomas 'PointedEars' Lahn <PointedEars@web.de> - 2026-08-01 04:10 +0200
      Tablet and phone UBS-C remote debugging (Re: Lamas in a cradle and Lamas on the edge [Red Pyjama]) Mild Shock <janburse@fastmail.fm> - 2026-08-01 12:17 +0200
        NPUs doing 2d chess comms (Manhattan Distance or L1 Norm) (Was: Tablet and phone UBS-C remote debugging) Mild Shock <janburse@fastmail.fm> - 2026-08-01 14:09 +0200
          First AI laptops, now AI single-boarders [Budget, Budget, ..] (Re: NPUs doing 2d chess comms (Manhattan Distance or L1 Norm) Mild Shock <janburse@fastmail.fm> - 2026-08-26 00:08 +0200
            Food for thought: ISOMICRO profile of Web Prolog (Was: First AI laptops, now AI single-boarders [Budget, Budget, ..]) Mild Shock <janburse@fastmail.fm> - 2026-08-31 18:03 +0200
              Food for thought: Le Petit Bistro as a Trinity Use Case (Re: Food for thought: ISOMICRO profile of Web Prolog) Mild Shock <janburse@fastmail.fm> - 2026-09-02 21:52 +0200
                Giga Lips for Prolog based Chatting (Re: Food for thought: Le Petit Bistro as a Trinity Use Case) Mild Shock <janburse@fastmail.fm> - 2026-09-02 21:56 +0200
                  Google holds the keys to the AI kingdom [WebClaw Dominance] (Re: Giga Lips for Prolog based Chatting) Mild Shock <janburse@fastmail.fm> - 2026-09-03 09:46 +0200
        Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging) Mild Shock <janburse@fastmail.fm> - 2026-08-02 02:47 +0200
          npm install webgpu [Google Dawn] (Was: Chris M. Thomasson can ask 100 more questions) Mild Shock <janburse@fastmail.fm> - 2026-08-02 03:01 +0200
            GPU elasticity was already invented in 2008 with CUDA (Re: npm install webgpu [Google Dawn]) Mild Shock <janburse@fastmail.fm> - 2026-08-02 23:59 +0200
          Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging) Johann 'Myrkraverk' Oskarsson <johann@myrkraverk.invalid> - 2026-08-03 00:34 +0800
            Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-02 10:41 -0700
              Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-08-02 11:13 -0700
          Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2026-08-02 12:42 -0700
            You posted that already, but you didn't listen [I NEED BOUNDED QUEUES] (Was: Chris M. Thomasson can ask 100 more questions) Mild Shock <janburse@fastmail.fm> - 2026-08-02 23:09 +0200
              Summary of 100 questions Chris M. Thomasson can ask (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES]) Mild Shock <janburse@fastmail.fm> - 2026-08-02 23:17 +0200
              Summary of 100 questions Chris M. Thomasson can ask (Re: You posted that already, but you didn't listen) Mild Shock <janburse@fastmail.fm> - 2026-08-02 23:20 +0200
              Re: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES] (Was: Chris M. Thomasson can ask 100 more questions) "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com> - 2026-08-03 12:55 -0700
                Liar and spammer (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES]) Mild Shock <janburse@fastmail.fm> - 2026-08-03 22:16 +0200
                  Re: Liar and spammer (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES]) Rosalino Kablahov <oaror@vla.ru> - 2026-08-03 21:50 +0000
      Synthetic Multilanguage Autoformalization Dataset [Informath project] (Re: Lamas in a cradle and Lamas on the edge [Red Pyjama] ) Mild Shock <janburse@fastmail.fm> - 2026-08-08 09:21 +0200
        Six Proofs and Generally Inteligent Systems [EyeProlog Pseudo Scientism] (Was: Synthetic Multilanguage Autoformalization Dataset [Informath project] (Re: Lamas in a cradle and Lamas on the edge [Red Pyjama] ) Mild Shock <janburse@fastmail.fm> - 2026-08-15 15:17 +0200
          Everybody does eat and sleep [The SK hynix Story] (Re: Six Proofs and Generally Inteligent Systems [EyeProlog Pseudo Scientism]) Mild Shock <janburse@fastmail.fm> - 2026-08-15 18:49 +0200
    Even send_color and recv_color can block [Cerebras Waver] Re: The Wuhan Virus that destroyed Python [ggml Manifesto] Mild Shock <janburse@fastmail.fm> - 2026-08-02 23:33 +0200
    GPU Elasticity: Collective Communications Libraries (Was: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-08-07 14:34 +0200
      What are Flits and Phits? [Network on a Chip] (Re: GPU Elasticity: Collective Communications Libraries) Mild Shock <janburse@fastmail.fm> - 2026-08-07 18:06 +0200
        The Mac Neo is a Budget Monster [GPU Channels] (Was: What are Flits and Phits? [Network on a Chip]) Mild Shock <janburse@fastmail.fm> - 2026-08-11 16:23 +0200
          The luminaries of duct-tape engineering [Sweeney and Torvald] (Re: The Mac Neo is a Budget Monster [GPU Channels]) Mild Shock <janburse@fastmail.fm> - 2026-08-11 16:56 +0200
          Re: The Mac Neo is a Budget Monster [GPU Channels] (Was: What are Flits and Phits? [Network on a Chip]) Ariquer Mihailov <ii@eor.ru> - 2026-08-11 15:16 +0000
    Cristallina: Thank you for the Beam (Re: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-08-09 21:21 +0200
      Giant Shoulders for AI Surprises (Re: Cristallina: Thank you for the Beam) Mild Shock <janburse@fastmail.fm> - 2026-08-18 14:58 +0200
        Loderunner Enemy AI better than SWI-Prolog? [Prolog Education Group] Mild Shock <janburse@fastmail.fm> - 2026-08-18 16:24 +0200
          How to shoot yourself in the foot (Re: Loderunner Enemy AI better than SWI-Prolog?) Mild Shock <janburse@fastmail.fm> - 2026-08-18 16:47 +0200
          Re: Loderunner Enemy AI better than SWI-Prolog? [Prolog Education Group] Lane W <cactus_DAC@yahoo.com> - 2026-08-18 08:59 -0600
          William A. Howard solved all his 99 problems (Was: Loderunner Enemy AI better than SWI-Prolog?) Mild Shock <janburse@fastmail.fm> - 2026-08-23 01:46 +0200
    Harmonic Analysis collides with Gabriels Horn [9-11 Math Incident] (Was: Accelerate Lean! From Theorem 3.11 to Corollary 3.12 [ZMC]) Mild Shock <janburse@fastmail.fm> - 2026-09-11 20:40 +0200
      Math has found a new Muse [Grothendieck Hodges] (Re: Harmonic Analysis collides with Gabriels Horn) Mild Shock <janburse@fastmail.fm> - 2026-09-12 11:27 +0200
        Kurzweils prognostic failure [Nabokov Fallacy] (Re: Math has found a new Muse [Grothendieck Hodges] (Re: Harmonic Analysis collides with Gabriels Horn)) Mild Shock <janburse@fastmail.fm> - 2026-09-12 12:11 +0200
    Mojo: The Small Hands Paradox [Maastrichtian Stage] (Re: The Wuhan Virus that destroyed Python [ggml Manifesto]) Mild Shock <janburse@fastmail.fm> - 2026-09-15 14:33 +0200
      More from the Trailer Park Boys (Was: Mojo: The Small Hands Paradox) Mild Shock <janburse@fastmail.fm> - 2026-09-15 19:41 +0200
        Interdisplinary Research for kill -9 (SIGKILL) (Re: More from the Trailer Park Boys) Mild Shock <janburse@fastmail.fm> - 2026-09-16 13:27 +0200
          Re: Interdisplinary Research for kill -9 (SIGKILL) (Re: More from the Trailer Park Boys) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-09-16 08:41 -0700
            Re: Interdisplinary Research for kill -9 (SIGKILL) (Re: More from the Trailer Park Boys) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-09-16 09:44 -0700
              Re: Interdisplinary Research for kill -9 (SIGKILL) (Re: More from the Trailer Park Boys) Ross Finlayson <ross.a.finlayson@gmail.com> - 2026-09-17 09:40 -0700
          Kundalini III: Modus Barbara versus Stock Pumping (Was: Interdisplinary Research for kill -9 (SIGKILL)) Mild Shock <janburse@fastmail.fm> - 2026-09-19 13:01 +0200
            Re: Kundalini III: Modus Barbara versus Stock Pumping (Was: Interdisplinary Research for kill -9 (SIGKILL)) Walton Havanov <nnht@vla.ru> - 2026-09-19 16:02 +0000
            The A2A project: Agent cards for collaboration (Was: A real Terence Tao Ingestion Problem) Mild Shock <janburse@fastmail.fm> - 2026-09-22 16:26 +0200
              Re: The A2A project: Agent cards for collaboration (Was: A real Terence Tao Ingestion Problem) Johann 'Myrkraverk' Oskarsson <johann@myrkraverk.invalid> - 2026-09-23 00:36 +0800
          Re: Interdisplinary Research for kill -9 (SIGKILL) (Re: More from the Trailer Park Boys) Branden Baraboshkin <naoea@kiadi.ru> - 2026-09-19 15:39 +0000
      Self censoring of not talking "superintelligence" (Was: Mojo: The Small Hands Paradox [Maastrichtian Stage]) Mild Shock <janburse@fastmail.fm> - 2026-09-22 18:03 +0200
        The Ben Goertzel talkie genes (Was: Re: Self censoring of not talking "superintelligence") Mild Shock <janburse@fastmail.fm> - 2026-09-22 18:05 +0200

Page 7 of 9 — ← Prev page 1 2 3 4 5 6 [7] 8 9  Next page →


#671763 — Can library(ironpaw) repurpose FFT hardware [Glimps into Ryzen AI 7 350] (Was: Actor/Erlang is dead, no Thread and Mailbox conflation)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-01 02:29 +0200
SubjectCan library(ironpaw) repurpose FFT hardware [Glimps into Ryzen AI 7 350] (Was: Actor/Erlang is dead, no Thread and Mailbox conflation)
Message-ID<114jem4$o8qj$1@solani.org>
In reply to#671730
Hi,

On could believe the AI boom is a kind of
Charles Darvin Galapagos Island Evolution
Trick of repurposing FFT hardware.

But this is of course not true, HPC, high
performance computing, has already defined
level 3 ops years ago.

But look at this rabit hole of Ryzen AI 7 350
NPU design, which is a stripped down Xilinx,
stripped of exotic FFT features:

Getting peak TOPS on a Ryzen AI 7 350 NPU
https://destevez.net/2026/05/getting-peak-tops-on-a-ryzen-ai-7-350-npu/

But the core feature, very long instruction
word (VLIW) engines, with hardware accelerated
GEMMs, scattered in grids of ASIC tiles,

connected by DMA and NoC, is even not very
specific to AMD, you find it also in Snapdragon /
Qualcomm SoCs for AI Laptops.

Bye

P.S.: My brain playing tricks, why should I
name a library(ironpaw) ? From the same
article above. Maybe WebNN is easier to use?

"mlir-aie contains a Python framework called
IRON that generates LLVM MLIR code representing
a workload that runs on the NPU, including the
code that runs on each compute tile processor

and the configuration of DMAs and other hardware.
Kernels for the compute tile processor can be
written in C++ and compiled either with the
open-source llvm-aie Peano compiler, which is

a fork of LLVM that adds support for the Xilinx
AI engine processors, or with the closed-source
Xilinx CHESS compiler, which is included in Vitis.
In simple cases the kernels can also be directly

written in Python with IRON."

Getting peak TOPS on a Ryzen AI 7 350 NPU
https://destevez.net/2026/05/getting-peak-tops-on-a-ryzen-ai-7-350-npu/


Mild Shock schrieb:
> Hi,
> 
> Mostlikely for high performance computing à la,
> the Actor/Erlang model is dead, they might rely
> on MPMC (Multiple Producer, Multiple Consumer)
> 
> queue entities separate from the threads. The
> ISO Prolog multi-threading support had also such
> threads. But besides that was also Actor/Erlang
> 
> leaning in practice, like SWI, where threads
> have some default queues. So an actor is basically
> a Thread and Mailbox conflation. While a MPMC queue
> 
> is a kind of separate Mailbox, where multiple
> "actors" can read from and write from. A kind of
> localized Linda Tuple store.
> 
> Which Programming language did adopted the
> non-Actor pi-calculus model? Right golang
> with its channels.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Usual question:
>>
>>  > Why implement both pre-emptive threading
>> AND cooperative tasks/engines?
>>
>> I had implemented the ISO proposal in formerly Jekejeke
>> Prolog, you find the ISO proposal here:
>>
>> ISO/IEC DTR 13211–5:2007
>> Prolog multi-threading support
>> https://logtalk.org/plstd/threads.pdf
>>
>> But the ISO proposal doesn't match modern WebGPU APIs,
>> where your logical threads can live remotely in a dedicated GPU
>> in the VRAM there, and where you would have launch
>>
>> parameters that say: Hey please run 4096 compute
>> shaders for me, that have independet thread state. Using
>> cooperative multi-tasking as the orchestrator works well.
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Why does this Lama have a red pyjama.
>>> Oh, its a baby Lama. Its still in the cradle
>>> and needs some training:
>>>
>>> RedPajama-Data-v2
>>> https://github.com/togethercomputer/RedPajama-Data
>>>
>>> But then Andrej Karpathy recently showed
>>> GPT-2 training on rented GPUs for less
>>> than 100 USD in less then 2 hours.
>>>
>>> So where do these grown up Lamas go.
>>> Well Georgi Gerganov prefered C++/C
>>> when he shouted Llama Llama Red Pyjama.
>>>
>>> But you also find WebLLM, wrapping the
>>> underlying C++/C GPU interface via the
>>> W3C standard WebGPU / WGSL, with JavaScript:
>>>
>>> In-Browser LLM Inference Engine
>>> https://webllm.mlc.ai/
>>>
>>> My experience with WebLLM 6 months
>>> ago on an iPad Pro 2024, still a little early
>>> stage performance and robustness.
>>>
>>> But hey hardware of AI mobile iGPUs is
>>> still evolving, and AI laptop, AI smartphones
>>> and AI tablets, will soon feature Chinese
>>>
>>> hardware such some new Kirin AI in 2027.
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> Remember when first all local AI was Python
>>>> and PyTorch APIs. And then suddently people strated
>>>> using bare metal C/C++ Code. Here is the story:
>>>>
>>>> How it started:
>>>>
>>>> GPT-J or GPT-J-6B is an open-source large
>>>> language model (LLM) developed by EleutherAI
>>>> in 2021. As the name suggests, it is a
>>>> generative pre-trained transformer model
>>>> designed to produce human-like text that
>>>> continues from a prompt.
>>>> https://www.eleuther.ai/
>>>>
>>>> How it was going [Georgi Gerganov]:
>>>>
>>>> So a few days later comes out the LLaMA, I do
>>>> some calculations and I figure out “Okay, 65
>>>> billion parameters. You probably need about
>>>> 40 gigs of RAM, with 4-bit quantization. So
>>>> this can run on a MacBook. Why not do it?”
>>>>
>>>> Why I was able to do it so quickly - basically,
>>>> for all that I saw it’s pretty much GPT-J architecture
>>>> with some modifications, like some extra memorization
>>>> layers. It’s minor changes. Basically, again, the
>>>> existing code for the GPT-J, I just simply
>>>> modified it there, it happened pretty quickly.
>>>> https://changelog.com/podcast/532
>>>>
>>>> Georgi Gerganov, Bulgarian, now with Hugging
>>>> Face, ggml-cann also running on Chinese AI chips.
>>>> ggml Manifesto https://github.com/ggml-org/ggml
>>>>
>>>> Bye
>>>>
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]


#671764 — Re: Can library(ironpaw) repurpose FFT hardware [Glimps into Ryzen AI 7 350]

FromThomas 'PointedEars' Lahn <PointedEars@web.de>
Date2026-08-01 04:10 +0200
SubjectRe: Can library(ironpaw) repurpose FFT hardware [Glimps into Ryzen AI 7 350]
Message-ID<114jkjd$9c3u$1@gwaiyur.mb-net.net>
In reply to#671763
Mild Shock wrote:
^^^^^^^^^^
Your real name belongs there.

> On could believe the AI boom is a kind of
> Charles Darvin Galapagos Island Evolution
> Trick of repurposing FFT hardware. [...]

What is the relation of this to the theories of relativity?

If none, then stop crossposting to sci.physics.relativity
(before someone makes you to).

Also, the "(was: ...)" in the Subject must be written _lowercase_ if it is
to be automatically removed by NetNews user agents like
Thunderbird/Betterbird on Follow-up.

F'up2 sci.physics.relativity

-- 
PointedEars

Twitter: @PointedEars2
Please do not cc me. / Bitte keine Kopien per E-Mail.

[toc] | [prev] | [next] | [standalone]


#671770 — Tablet and phone UBS-C remote debugging (Re: Lamas in a cradle and Lamas on the edge [Red Pyjama])

FromMild Shock <janburse@fastmail.fm>
Date2026-08-01 12:17 +0200
SubjectTablet and phone UBS-C remote debugging (Re: Lamas in a cradle and Lamas on the edge [Red Pyjama])
Message-ID<114kh3m$ovdp$3@solani.org>
In reply to#671725
Hi,

Tablets and phone are more annoying to
use with WebGPU. The usual browsers don't
have a Chrome DevTools panel integrated,

so that one could do JavaScript Debugging
directly on the device. Instead one has to
use a desktop machine, and connect the

device via UBS-C , and start a Chrome
Browser there . And then start a Chrome
DevTools panel alone, that is pair with

the device, via UBS-C cable. So this way
I already see where it crashes on the
tablets and phone:

await output.mapAsync(GPUMapMode.READ)
Unhandled Promise Rejection: OperationError

The above is the error that one can re-produce
already here with this test:

11.4 Giga Lips with a Budget Laptop
https://github.com/Jean-Luc-Picard-2021/gigabudget

Not sure what exactly happens. Maybe
a form of timeout or device lost, that the
primitive HTML / JavaScript doesn't handle

gracefully yet. Maybe redimensioning the
test, so that it consumes less time would
help. Who knows? Will see. For production

use of a GPU integration I have to anyway
provide work slicing it seems.

Bye

Mild Shock schrieb:
> Hi,
> 
> Why does this Lama have a red pyjama.
> Oh, its a baby Lama. Its still in the cradle
> and needs some training:
> 
> RedPajama-Data-v2
> https://github.com/togethercomputer/RedPajama-Data
> 
> But then Andrej Karpathy recently showed
> GPT-2 training on rented GPUs for less
> than 100 USD in less then 2 hours.
> 
> So where do these grown up Lamas go.
> Well Georgi Gerganov prefered C++/C
> when he shouted Llama Llama Red Pyjama.
> 
> But you also find WebLLM, wrapping the
> underlying C++/C GPU interface via the
> W3C standard WebGPU / WGSL, with JavaScript:
> 
> In-Browser LLM Inference Engine
> https://webllm.mlc.ai/
> 
> My experience with WebLLM 6 months
> ago on an iPad Pro 2024, still a little early
> stage performance and robustness.
> 
> But hey hardware of AI mobile iGPUs is
> still evolving, and AI laptop, AI smartphones
> and AI tablets, will soon feature Chinese
> 
> hardware such some new Kirin AI in 2027.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Remember when first all local AI was Python
>> and PyTorch APIs. And then suddently people strated
>> using bare metal C/C++ Code. Here is the story:
>>
>> How it started:
>>
>> GPT-J or GPT-J-6B is an open-source large
>> language model (LLM) developed by EleutherAI
>> in 2021. As the name suggests, it is a
>> generative pre-trained transformer model
>> designed to produce human-like text that
>> continues from a prompt.
>> https://www.eleuther.ai/
>>
>> How it was going [Georgi Gerganov]:
>>
>> So a few days later comes out the LLaMA, I do
>> some calculations and I figure out “Okay, 65
>> billion parameters. You probably need about
>> 40 gigs of RAM, with 4-bit quantization. So
>> this can run on a MacBook. Why not do it?”
>>
>> Why I was able to do it so quickly - basically,
>> for all that I saw it’s pretty much GPT-J architecture
>> with some modifications, like some extra memorization
>> layers. It’s minor changes. Basically, again, the
>> existing code for the GPT-J, I just simply
>> modified it there, it happened pretty quickly.
>> https://changelog.com/podcast/532
>>
>> Georgi Gerganov, Bulgarian, now with Hugging
>> Face, ggml-cann also running on Chinese AI chips.
>> ggml Manifesto https://github.com/ggml-org/ggml
>>
>> Bye
>>
> 

[toc] | [prev] | [next] | [standalone]


#671772 — NPUs doing 2d chess comms (Manhattan Distance or L1 Norm) (Was: Tablet and phone UBS-C remote debugging)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-01 14:09 +0200
SubjectNPUs doing 2d chess comms (Manhattan Distance or L1 Norm) (Was: Tablet and phone UBS-C remote debugging)
Message-ID<114knku$pjus$1@solani.org>
In reply to#671770
Hi,

Looking at the floor plan of a NPU:

Getting peak TOPS on a Ryzen AI 7 350 NPU
https://destevez.net/2026/05/getting-peak-tops-on-a-ryzen-ai-7-350-npu/

It seems to me comms between tiles takes
at least Manhattan Distance or L1 Norm time,
if there is no comms congestion

But how does a packet travel? This way:

+----E
|
|
S

Or this way, from start S to end E:

    +-E
   +
  +
S

And what does the chip do if there is
traffic congestion? Some papers are
here, possibly an old problem giving

that processor "cubes" are nothing new.
But a "cube" would be 3D and not 2D.
This paper is old from 2007 or so:

Routing Algorithms for 2D NoC Architectures
http://cva.stanford.edu/classes/ee382c/research/2DRouting.pdf

Bye

Mild Shock schrieb:
> Hi,
> 
> Tablets and phone are more annoying to
> use with WebGPU. The usual browsers don't
> have a Chrome DevTools panel integrated,
> 
> so that one could do JavaScript Debugging
> directly on the device. Instead one has to
> use a desktop machine, and connect the
> 
> device via UBS-C , and start a Chrome
> Browser there . And then start a Chrome
> DevTools panel alone, that is pair with
> 
> the device, via UBS-C cable. So this way
> I already see where it crashes on the
> tablets and phone:
> 
> await output.mapAsync(GPUMapMode.READ)
> Unhandled Promise Rejection: OperationError
> 
> The above is the error that one can re-produce
> already here with this test:
> 
> 11.4 Giga Lips with a Budget Laptop
> https://github.com/Jean-Luc-Picard-2021/gigabudget
> 
> Not sure what exactly happens. Maybe
> a form of timeout or device lost, that the
> primitive HTML / JavaScript doesn't handle
> 
> gracefully yet. Maybe redimensioning the
> test, so that it consumes less time would
> help. Who knows? Will see. For production
> 
> use of a GPU integration I have to anyway
> provide work slicing it seems.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Why does this Lama have a red pyjama.
>> Oh, its a baby Lama. Its still in the cradle
>> and needs some training:
>>
>> RedPajama-Data-v2
>> https://github.com/togethercomputer/RedPajama-Data
>>
>> But then Andrej Karpathy recently showed
>> GPT-2 training on rented GPUs for less
>> than 100 USD in less then 2 hours.
>>
>> So where do these grown up Lamas go.
>> Well Georgi Gerganov prefered C++/C
>> when he shouted Llama Llama Red Pyjama.
>>
>> But you also find WebLLM, wrapping the
>> underlying C++/C GPU interface via the
>> W3C standard WebGPU / WGSL, with JavaScript:
>>
>> In-Browser LLM Inference Engine
>> https://webllm.mlc.ai/
>>
>> My experience with WebLLM 6 months
>> ago on an iPad Pro 2024, still a little early
>> stage performance and robustness.
>>
>> But hey hardware of AI mobile iGPUs is
>> still evolving, and AI laptop, AI smartphones
>> and AI tablets, will soon feature Chinese
>>
>> hardware such some new Kirin AI in 2027.
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Remember when first all local AI was Python
>>> and PyTorch APIs. And then suddently people strated
>>> using bare metal C/C++ Code. Here is the story:
>>>
>>> How it started:
>>>
>>> GPT-J or GPT-J-6B is an open-source large
>>> language model (LLM) developed by EleutherAI
>>> in 2021. As the name suggests, it is a
>>> generative pre-trained transformer model
>>> designed to produce human-like text that
>>> continues from a prompt.
>>> https://www.eleuther.ai/
>>>
>>> How it was going [Georgi Gerganov]:
>>>
>>> So a few days later comes out the LLaMA, I do
>>> some calculations and I figure out “Okay, 65
>>> billion parameters. You probably need about
>>> 40 gigs of RAM, with 4-bit quantization. So
>>> this can run on a MacBook. Why not do it?”
>>>
>>> Why I was able to do it so quickly - basically,
>>> for all that I saw it’s pretty much GPT-J architecture
>>> with some modifications, like some extra memorization
>>> layers. It’s minor changes. Basically, again, the
>>> existing code for the GPT-J, I just simply
>>> modified it there, it happened pretty quickly.
>>> https://changelog.com/podcast/532
>>>
>>> Georgi Gerganov, Bulgarian, now with Hugging
>>> Face, ggml-cann also running on Chinese AI chips.
>>> ggml Manifesto https://github.com/ggml-org/ggml
>>>
>>> Bye
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]


#672421 — First AI laptops, now AI single-boarders [Budget, Budget, ..] (Re: NPUs doing 2d chess comms (Manhattan Distance or L1 Norm)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-26 00:08 +0200
SubjectFirst AI laptops, now AI single-boarders [Budget, Budget, ..] (Re: NPUs doing 2d chess comms (Manhattan Distance or L1 Norm)
Message-ID<116l3oe$13osq$2@solani.org>
In reply to#671772
Hi,

Ok, that was quick. While my AI Laptops were
around > 1000 CHF. The Mac Neo was around
 > 500 CHF. So we went already form AI Laptop

to AI Notebook in a few months. Now Aduino
is playing pionier, having a CPU with a NPU
on board, some Qualcomm thingy.

New Arduino Ventuno Q: Better than Raspberry Pi?
https://www.youtube.com/watch?v=qQS_xWsU00I

The specs:

Octa-core ARM Cortex CPU
Adreno GPU and Hexagon AI processor (up to 40 TOPS)
16GB LPDDR5 RAM and 64GB eMMC storage
M.2 slot for NVMe SSD expansion

The cost is around 300 CHF.

Bye

Mild Shock schrieb:
> Hi,
> 
> Looking at the floor plan of a NPU:
> 
> Getting peak TOPS on a Ryzen AI 7 350 NPU
> https://destevez.net/2026/05/getting-peak-tops-on-a-ryzen-ai-7-350-npu/
> 
> It seems to me comms between tiles takes
> at least Manhattan Distance or L1 Norm time,
> if there is no comms congestion
> 
> But how does a packet travel? This way:
> 
> +----E
> |
> |
> S
> 
> Or this way, from start S to end E:
> 
>     +-E
>    +
>   +
> S
> 
> And what does the chip do if there is
> traffic congestion? Some papers are
> here, possibly an old problem giving
> 
> that processor "cubes" are nothing new.
> But a "cube" would be 3D and not 2D.
> This paper is old from 2007 or so:
> 
> Routing Algorithms for 2D NoC Architectures
> http://cva.stanford.edu/classes/ee382c/research/2DRouting.pdf
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Tablets and phone are more annoying to
>> use with WebGPU. The usual browsers don't
>> have a Chrome DevTools panel integrated,
>>
>> so that one could do JavaScript Debugging
>> directly on the device. Instead one has to
>> use a desktop machine, and connect the
>>
>> device via UBS-C , and start a Chrome
>> Browser there . And then start a Chrome
>> DevTools panel alone, that is pair with
>>
>> the device, via UBS-C cable. So this way
>> I already see where it crashes on the
>> tablets and phone:
>>
>> await output.mapAsync(GPUMapMode.READ)
>> Unhandled Promise Rejection: OperationError
>>
>> The above is the error that one can re-produce
>> already here with this test:
>>
>> 11.4 Giga Lips with a Budget Laptop
>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>
>> Not sure what exactly happens. Maybe
>> a form of timeout or device lost, that the
>> primitive HTML / JavaScript doesn't handle
>>
>> gracefully yet. Maybe redimensioning the
>> test, so that it consumes less time would
>> help. Who knows? Will see. For production
>>
>> use of a GPU integration I have to anyway
>> provide work slicing it seems.
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Why does this Lama have a red pyjama.
>>> Oh, its a baby Lama. Its still in the cradle
>>> and needs some training:
>>>
>>> RedPajama-Data-v2
>>> https://github.com/togethercomputer/RedPajama-Data
>>>
>>> But then Andrej Karpathy recently showed
>>> GPT-2 training on rented GPUs for less
>>> than 100 USD in less then 2 hours.
>>>
>>> So where do these grown up Lamas go.
>>> Well Georgi Gerganov prefered C++/C
>>> when he shouted Llama Llama Red Pyjama.
>>>
>>> But you also find WebLLM, wrapping the
>>> underlying C++/C GPU interface via the
>>> W3C standard WebGPU / WGSL, with JavaScript:
>>>
>>> In-Browser LLM Inference Engine
>>> https://webllm.mlc.ai/
>>>
>>> My experience with WebLLM 6 months
>>> ago on an iPad Pro 2024, still a little early
>>> stage performance and robustness.
>>>
>>> But hey hardware of AI mobile iGPUs is
>>> still evolving, and AI laptop, AI smartphones
>>> and AI tablets, will soon feature Chinese
>>>
>>> hardware such some new Kirin AI in 2027.
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> Remember when first all local AI was Python
>>>> and PyTorch APIs. And then suddently people strated
>>>> using bare metal C/C++ Code. Here is the story:
>>>>
>>>> How it started:
>>>>
>>>> GPT-J or GPT-J-6B is an open-source large
>>>> language model (LLM) developed by EleutherAI
>>>> in 2021. As the name suggests, it is a
>>>> generative pre-trained transformer model
>>>> designed to produce human-like text that
>>>> continues from a prompt.
>>>> https://www.eleuther.ai/
>>>>
>>>> How it was going [Georgi Gerganov]:
>>>>
>>>> So a few days later comes out the LLaMA, I do
>>>> some calculations and I figure out “Okay, 65
>>>> billion parameters. You probably need about
>>>> 40 gigs of RAM, with 4-bit quantization. So
>>>> this can run on a MacBook. Why not do it?”
>>>>
>>>> Why I was able to do it so quickly - basically,
>>>> for all that I saw it’s pretty much GPT-J architecture
>>>> with some modifications, like some extra memorization
>>>> layers. It’s minor changes. Basically, again, the
>>>> existing code for the GPT-J, I just simply
>>>> modified it there, it happened pretty quickly.
>>>> https://changelog.com/podcast/532
>>>>
>>>> Georgi Gerganov, Bulgarian, now with Hugging
>>>> Face, ggml-cann also running on Chinese AI chips.
>>>> ggml Manifesto https://github.com/ggml-org/ggml
>>>>
>>>> Bye
>>>>
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]


#672600 — Food for thought: ISOMICRO profile of Web Prolog (Was: First AI laptops, now AI single-boarders [Budget, Budget, ..])

FromMild Shock <janburse@fastmail.fm>
Date2026-08-31 18:03 +0200
SubjectFood for thought: ISOMICRO profile of Web Prolog (Was: First AI laptops, now AI single-boarders [Budget, Budget, ..])
Message-ID<11748k3$1e7mp$3@solani.org>
In reply to#672421
Hi,

I miss an ISOMICRO profile of Web Prolog, a profile
that can run on small embedded devices, and only
single threaded. Like Python can do for example.

I deleted my previous post, since it drifted into
high performance computing. It was a reaction of
mine, to these results and how they were viewed.

Web Prolog result:

100,000 4.749 s

I get this here:

/* 100'000 iterations */
?- between(1,3,_), time(ping_pong), fail; true.
% Zeit 97.020 ms, Benutzer 2 %, Lips 735 k
% Zeit 95.040 ms, Benutzer 1 %, Lips 1057 k
% Zeit 98.740 ms, Benutzer 1 %, Lips 974 k
true.

But the results have a few drawbacks. They use a highly
specialized π-WAM Prolog subset and a highly specialized
Hack VM backend. Also the ping pong code was optimized.

So I guess this high performance view is too specifiec
for the actor model. So to get a more general comparison,
I tried something else. I used a Python implemented Prolog

and a Python asyncio.Future implemented one element
channels, the later equals SWI-Prolog queues with max_size=1.
Finally I used the classical ping pong. Now with PyPy as the Python

runtime the results are, 6x times faster than the shared database
on a SWI-Prolog server provided by Torbjörn Lager. Difficult
to judge maybe my machine is just 6x times faster? One could

install PyPy, download Dogelog Player and run it on the server:

?- between(1,3,_), time(ping_pong(100000)), fail; true.
% Time 812.000 ms, User 54 %, Lips 5977 k
% Time 703.000 ms, User 53 %, Lips 6915 k
% Time 766.000 ms, User 64 %, Lips 5339 k
true.

But this makes me ask, where would one see using for
example SWI-Prolog Engines for the actor model, so that it
becomes competitive to asyncio.Future? Any idea how to do it?

I guess asyncio.Future only uses a micro queue or something.
This would give the ISOMICRO profile of Web Prolog, a profile
that can run on small embedded devices single threaded.

The opposite of high preformance computing (HPC).

Bye

See also:

https://trinity.elfenbenstornet.se/

P.S.: Here the source code, first what was used for validation:

  classic ping pong with channels and with logging
And the validation output:

  log of running N=3
And what was used for benchmarking:

  classic ping pong with channels and without logging

Mild Shock schrieb:
 > Hi,
 >
 > Ok, that was quick. While my AI Laptops were
 > around > 1000 CHF. The Mac Neo was around
 >  > 500 CHF. So we went already form AI Laptop
 >
 > to AI Notebook in a few months. Now Aduino
 > is playing pionier, having a CPU with a NPU
 > on board, some Qualcomm thingy.
 >
 > New Arduino Ventuno Q: Better than Raspberry Pi?
 > https://www.youtube.com/watch?v=qQS_xWsU00I
 >
 > The specs:
 >
 > Octa-core ARM Cortex CPU
 > Adreno GPU and Hexagon AI processor (up to 40 TOPS)
 > 16GB LPDDR5 RAM and 64GB eMMC storage
 > M.2 slot for NVMe SSD expansion
 >
 > The cost is around 300 CHF.
 >
 > Bye

[toc] | [prev] | [next] | [standalone]


#672701 — Food for thought: Le Petit Bistro as a Trinity Use Case (Re: Food for thought: ISOMICRO profile of Web Prolog)

FromMild Shock <janburse@fastmail.fm>
Date2026-09-02 21:52 +0200
SubjectFood for thought: Le Petit Bistro as a Trinity Use Case (Re: Food for thought: ISOMICRO profile of Web Prolog)
Message-ID<1179uq0$1i7hp$2@solani.org>
In reply to#672600
Hi,

I really wonder what use cases Web Prolog trinity would
have. Would Web Prolog trinity reach in its scope into
the domain of AI chat bots inside a web page? Ok, google

has hijacked the term “declarative”, when an AI chatbot
assistant helps fill out a HTML form. And it uses the term
“imperative” when the AI chatbot calls JavaScript routines.

Could be related to the ACTOR model who knows. Although
the hijacking is not optimal, I like the thinking in levels, that are
related to states, just like Torbjörn Lager exercises in his 400

pages, although google does maybe a bender, when it calls
a form submit, and hence a HTTP POST, declarative.

Bye

See also:

WebMCP
https://developer.chrome.com/docs/ai/webmcp

Here the newly arrived browser integration:

Le Petit Bistro
https://googlechromelabs.github.io/webmcp-tools/demos/french-bistro

image

Mild Shock schrieb:
> Hi,
> 
> I miss an ISOMICRO profile of Web Prolog, a profile
> that can run on small embedded devices, and only
> single threaded. Like Python can do for example.
> 
> I deleted my previous post, since it drifted into
> high performance computing. It was a reaction of
> mine, to these results and how they were viewed.
> 
> Web Prolog result:
> 
> 100,000 4.749 s
> 
> I get this here:
> 
> /* 100'000 iterations */
> ?- between(1,3,_), time(ping_pong), fail; true.
> % Zeit 97.020 ms, Benutzer 2 %, Lips 735 k
> % Zeit 95.040 ms, Benutzer 1 %, Lips 1057 k
> % Zeit 98.740 ms, Benutzer 1 %, Lips 974 k
> true.
> 
> But the results have a few drawbacks. They use a highly
> specialized π-WAM Prolog subset and a highly specialized
> Hack VM backend. Also the ping pong code was optimized.
> 
> So I guess this high performance view is too specifiec
> for the actor model. So to get a more general comparison,
> I tried something else. I used a Python implemented Prolog
> 
> and a Python asyncio.Future implemented one element
> channels, the later equals SWI-Prolog queues with max_size=1.
> Finally I used the classical ping pong. Now with PyPy as the Python
> 
> runtime the results are, 6x times faster than the shared database
> on a SWI-Prolog server provided by Torbjörn Lager. Difficult
> to judge maybe my machine is just 6x times faster? One could
> 
> install PyPy, download Dogelog Player and run it on the server:
> 
> ?- between(1,3,_), time(ping_pong(100000)), fail; true.
> % Time 812.000 ms, User 54 %, Lips 5977 k
> % Time 703.000 ms, User 53 %, Lips 6915 k
> % Time 766.000 ms, User 64 %, Lips 5339 k
> true.
> 
> But this makes me ask, where would one see using for
> example SWI-Prolog Engines for the actor model, so that it
> becomes competitive to asyncio.Future? Any idea how to do it?
> 
> I guess asyncio.Future only uses a micro queue or something.
> This would give the ISOMICRO profile of Web Prolog, a profile
> that can run on small embedded devices single threaded.
> 
> The opposite of high preformance computing (HPC).
> 
> Bye
> 
> See also:
> 
> https://trinity.elfenbenstornet.se/
> 
> P.S.: Here the source code, first what was used for validation:
> 
>   classic ping pong with channels and with logging
> And the validation output:
> 
>   log of running N=3
> And what was used for benchmarking:
> 
>   classic ping pong with channels and without logging
> 
> Mild Shock schrieb:
>  > Hi,
>  >
>  > Ok, that was quick. While my AI Laptops were
>  > around > 1000 CHF. The Mac Neo was around
>  >  > 500 CHF. So we went already form AI Laptop
>  >
>  > to AI Notebook in a few months. Now Aduino
>  > is playing pionier, having a CPU with a NPU
>  > on board, some Qualcomm thingy.
>  >
>  > New Arduino Ventuno Q: Better than Raspberry Pi?
>  > https://www.youtube.com/watch?v=qQS_xWsU00I
>  >
>  > The specs:
>  >
>  > Octa-core ARM Cortex CPU
>  > Adreno GPU and Hexagon AI processor (up to 40 TOPS)
>  > 16GB LPDDR5 RAM and 64GB eMMC storage
>  > M.2 slot for NVMe SSD expansion
>  >
>  > The cost is around 300 CHF.
>  >
>  > Bye

[toc] | [prev] | [next] | [standalone]


#672702 — Giga Lips for Prolog based Chatting (Re: Food for thought: Le Petit Bistro as a Trinity Use Case)

FromMild Shock <janburse@fastmail.fm>
Date2026-09-02 21:56 +0200
SubjectGiga Lips for Prolog based Chatting (Re: Food for thought: Le Petit Bistro as a Trinity Use Case)
Message-ID<1179v1g$1i7hp$6@solani.org>
In reply to#672701
Hi,

What if a Prolog system can draw enough processing power,
by tapping into the GPU of budget laptop that shows the
web page? And run locally in a ServiceWorker. The WebMCP

use case Le Petit Bistro is already such that it also has a
ServiceWorker for the Gemini stub. But the envisioned variant of a
ISOMICRO model would neither need a Gemini API token,

nor would it need WebSockets or HTTP for communication. It
would all be WebMCP inside the conglomerate of website and
workers. The small language model is loaded into the ServiceWorker

and run on the GPU. Here my contribution to this idea:

11.4 Giga Lips with a Budget Laptop
https://github.com/Jean-Luc-Picard-2021/gigabudget

Work in progress cannot demonstrate a Prolog assistant yet.

Bye

Mild Shock schrieb:
> Hi,
> 
> I really wonder what use cases Web Prolog trinity would
> have. Would Web Prolog trinity reach in its scope into
> the domain of AI chat bots inside a web page? Ok, google
> 
> has hijacked the term “declarative”, when an AI chatbot
> assistant helps fill out a HTML form. And it uses the term
> “imperative” when the AI chatbot calls JavaScript routines.
> 
> Could be related to the ACTOR model who knows. Although
> the hijacking is not optimal, I like the thinking in levels, that are
> related to states, just like Torbjörn Lager exercises in his 400
> 
> pages, although google does maybe a bender, when it calls
> a form submit, and hence a HTTP POST, declarative.
> 
> Bye
> 
> See also:
> 
> WebMCP
> https://developer.chrome.com/docs/ai/webmcp
> 
> Here the newly arrived browser integration:
> 
> Le Petit Bistro
> https://googlechromelabs.github.io/webmcp-tools/demos/french-bistro
> 
> image
> 
> Mild Shock schrieb:
>> Hi,
>>
>> I miss an ISOMICRO profile of Web Prolog, a profile
>> that can run on small embedded devices, and only
>> single threaded. Like Python can do for example.
>>
>> I deleted my previous post, since it drifted into
>> high performance computing. It was a reaction of
>> mine, to these results and how they were viewed.
>>
>> Web Prolog result:
>>
>> 100,000 4.749 s
>>
>> I get this here:
>>
>> /* 100'000 iterations */
>> ?- between(1,3,_), time(ping_pong), fail; true.
>> % Zeit 97.020 ms, Benutzer 2 %, Lips 735 k
>> % Zeit 95.040 ms, Benutzer 1 %, Lips 1057 k
>> % Zeit 98.740 ms, Benutzer 1 %, Lips 974 k
>> true.
>>
>> But the results have a few drawbacks. They use a highly
>> specialized π-WAM Prolog subset and a highly specialized
>> Hack VM backend. Also the ping pong code was optimized.
>>
>> So I guess this high performance view is too specifiec
>> for the actor model. So to get a more general comparison,
>> I tried something else. I used a Python implemented Prolog
>>
>> and a Python asyncio.Future implemented one element
>> channels, the later equals SWI-Prolog queues with max_size=1.
>> Finally I used the classical ping pong. Now with PyPy as the Python
>>
>> runtime the results are, 6x times faster than the shared database
>> on a SWI-Prolog server provided by Torbjörn Lager. Difficult
>> to judge maybe my machine is just 6x times faster? One could
>>
>> install PyPy, download Dogelog Player and run it on the server:
>>
>> ?- between(1,3,_), time(ping_pong(100000)), fail; true.
>> % Time 812.000 ms, User 54 %, Lips 5977 k
>> % Time 703.000 ms, User 53 %, Lips 6915 k
>> % Time 766.000 ms, User 64 %, Lips 5339 k
>> true.
>>
>> But this makes me ask, where would one see using for
>> example SWI-Prolog Engines for the actor model, so that it
>> becomes competitive to asyncio.Future? Any idea how to do it?
>>
>> I guess asyncio.Future only uses a micro queue or something.
>> This would give the ISOMICRO profile of Web Prolog, a profile
>> that can run on small embedded devices single threaded.
>>
>> The opposite of high preformance computing (HPC).
>>
>> Bye
>>
>> See also:
>>
>> https://trinity.elfenbenstornet.se/
>>
>> P.S.: Here the source code, first what was used for validation:
>>
>>   classic ping pong with channels and with logging
>> And the validation output:
>>
>>   log of running N=3
>> And what was used for benchmarking:
>>
>>   classic ping pong with channels and without logging
>>
>> Mild Shock schrieb:
>>  > Hi,
>>  >
>>  > Ok, that was quick. While my AI Laptops were
>>  > around > 1000 CHF. The Mac Neo was around
>>  >  > 500 CHF. So we went already form AI Laptop
>>  >
>>  > to AI Notebook in a few months. Now Aduino
>>  > is playing pionier, having a CPU with a NPU
>>  > on board, some Qualcomm thingy.
>>  >
>>  > New Arduino Ventuno Q: Better than Raspberry Pi?
>>  > https://www.youtube.com/watch?v=qQS_xWsU00I
>>  >
>>  > The specs:
>>  >
>>  > Octa-core ARM Cortex CPU
>>  > Adreno GPU and Hexagon AI processor (up to 40 TOPS)
>>  > 16GB LPDDR5 RAM and 64GB eMMC storage
>>  > M.2 slot for NVMe SSD expansion
>>  >
>>  > The cost is around 300 CHF.
>>  >
>>  > Bye
> 

[toc] | [prev] | [next] | [standalone]


#672712 — Google holds the keys to the AI kingdom [WebClaw Dominance] (Re: Giga Lips for Prolog based Chatting)

FromMild Shock <janburse@fastmail.fm>
Date2026-09-03 09:46 +0200
SubjectGoogle holds the keys to the AI kingdom [WebClaw Dominance] (Re: Giga Lips for Prolog based Chatting)
Message-ID<117b8ko$1je8u$2@solani.org>
In reply to#672702
Hi,

You thought kubernets holds the keys to the
enterprise kingdom. Then you were bombarded
by OpenClaws, PrologAgents and WebPrologs,
over the last months.

Now from a market perspective and how devtools and
google controls browsers, despite there exists
the living standard for the non-devtools part.
The devtools part becomes the trust part.

The W3C specs can mandate all the clean, open
standards they want on paper, but whoever controls
the runtime inspector, the policy enforcement hooks,
and the agentic debugging surface inside

the browser holds the real keys to the kingdom.
When an AI agent interacts with a page via something
like navigator.modelContext, the trust doesn't come from
the living standard text — it comes from the browser

vendor's DevTools inspecting the schema, auditing the
tool execution payloads, and enforcing the security
boundaries. Google now dictates the trust model
precisely because they control how those tool
contracts are verified, sandboxed, and

certified in practice.

Bye

BTW: They have also a nice interaction inspector,
to play around with your website and AI assitant
combo. It looks not exactly like what the MCP

foundation had and what was copied by WebProlog,
with their log tiles. It combines the "declarative"/
"interactive" interaction with the NLP Text interaction:

WebMCP - Model Context Tool Inspector
https://chromewebstore.google.com/detail/webmcp-model-context-tool/gbpdfapgefenggkahomfgkhfehlcenpd

Mild Shock schrieb:
> Hi,
> 
> What if a Prolog system can draw enough processing power,
> by tapping into the GPU of budget laptop that shows the
> web page? And run locally in a ServiceWorker. The WebMCP
> 
> use case Le Petit Bistro is already such that it also has a
> ServiceWorker for the Gemini stub. But the envisioned variant of a
> ISOMICRO model would neither need a Gemini API token,
> 
> nor would it need WebSockets or HTTP for communication. It
> would all be WebMCP inside the conglomerate of website and
> workers. The small language model is loaded into the ServiceWorker
> 
> and run on the GPU. Here my contribution to this idea:
> 
> 11.4 Giga Lips with a Budget Laptop
> https://github.com/Jean-Luc-Picard-2021/gigabudget
> 
> Work in progress cannot demonstrate a Prolog assistant yet.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> I really wonder what use cases Web Prolog trinity would
>> have. Would Web Prolog trinity reach in its scope into
>> the domain of AI chat bots inside a web page? Ok, google
>>
>> has hijacked the term “declarative”, when an AI chatbot
>> assistant helps fill out a HTML form. And it uses the term
>> “imperative” when the AI chatbot calls JavaScript routines.
>>
>> Could be related to the ACTOR model who knows. Although
>> the hijacking is not optimal, I like the thinking in levels, that are
>> related to states, just like Torbjörn Lager exercises in his 400
>>
>> pages, although google does maybe a bender, when it calls
>> a form submit, and hence a HTTP POST, declarative.
>>
>> Bye
>>
>> See also:
>>
>> WebMCP
>> https://developer.chrome.com/docs/ai/webmcp
>>
>> Here the newly arrived browser integration:
>>
>> Le Petit Bistro
>> https://googlechromelabs.github.io/webmcp-tools/demos/french-bistro
>>
>> image
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> I miss an ISOMICRO profile of Web Prolog, a profile
>>> that can run on small embedded devices, and only
>>> single threaded. Like Python can do for example.
>>>
>>> I deleted my previous post, since it drifted into
>>> high performance computing. It was a reaction of
>>> mine, to these results and how they were viewed.
>>>
>>> Web Prolog result:
>>>
>>> 100,000 4.749 s
>>>
>>> I get this here:
>>>
>>> /* 100'000 iterations */
>>> ?- between(1,3,_), time(ping_pong), fail; true.
>>> % Zeit 97.020 ms, Benutzer 2 %, Lips 735 k
>>> % Zeit 95.040 ms, Benutzer 1 %, Lips 1057 k
>>> % Zeit 98.740 ms, Benutzer 1 %, Lips 974 k
>>> true.
>>>
>>> But the results have a few drawbacks. They use a highly
>>> specialized π-WAM Prolog subset and a highly specialized
>>> Hack VM backend. Also the ping pong code was optimized.
>>>
>>> So I guess this high performance view is too specifiec
>>> for the actor model. So to get a more general comparison,
>>> I tried something else. I used a Python implemented Prolog
>>>
>>> and a Python asyncio.Future implemented one element
>>> channels, the later equals SWI-Prolog queues with max_size=1.
>>> Finally I used the classical ping pong. Now with PyPy as the Python
>>>
>>> runtime the results are, 6x times faster than the shared database
>>> on a SWI-Prolog server provided by Torbjörn Lager. Difficult
>>> to judge maybe my machine is just 6x times faster? One could
>>>
>>> install PyPy, download Dogelog Player and run it on the server:
>>>
>>> ?- between(1,3,_), time(ping_pong(100000)), fail; true.
>>> % Time 812.000 ms, User 54 %, Lips 5977 k
>>> % Time 703.000 ms, User 53 %, Lips 6915 k
>>> % Time 766.000 ms, User 64 %, Lips 5339 k
>>> true.
>>>
>>> But this makes me ask, where would one see using for
>>> example SWI-Prolog Engines for the actor model, so that it
>>> becomes competitive to asyncio.Future? Any idea how to do it?
>>>
>>> I guess asyncio.Future only uses a micro queue or something.
>>> This would give the ISOMICRO profile of Web Prolog, a profile
>>> that can run on small embedded devices single threaded.
>>>
>>> The opposite of high preformance computing (HPC).
>>>
>>> Bye
>>>
>>> See also:
>>>
>>> https://trinity.elfenbenstornet.se/
>>>
>>> P.S.: Here the source code, first what was used for validation:
>>>
>>>   classic ping pong with channels and with logging
>>> And the validation output:
>>>
>>>   log of running N=3
>>> And what was used for benchmarking:
>>>
>>>   classic ping pong with channels and without logging
>>>
>>> Mild Shock schrieb:
>>>  > Hi,
>>>  >
>>>  > Ok, that was quick. While my AI Laptops were
>>>  > around > 1000 CHF. The Mac Neo was around
>>>  >  > 500 CHF. So we went already form AI Laptop
>>>  >
>>>  > to AI Notebook in a few months. Now Aduino
>>>  > is playing pionier, having a CPU with a NPU
>>>  > on board, some Qualcomm thingy.
>>>  >
>>>  > New Arduino Ventuno Q: Better than Raspberry Pi?
>>>  > https://www.youtube.com/watch?v=qQS_xWsU00I
>>>  >
>>>  > The specs:
>>>  >
>>>  > Octa-core ARM Cortex CPU
>>>  > Adreno GPU and Hexagon AI processor (up to 40 TOPS)
>>>  > 16GB LPDDR5 RAM and 64GB eMMC storage
>>>  > M.2 slot for NVMe SSD expansion
>>>  >
>>>  > The cost is around 300 CHF.
>>>  >
>>>  > Bye
>>
> 

[toc] | [prev] | [next] | [standalone]


#671785 — Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-02 02:47 +0200
SubjectChris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)
Message-ID<114m42n$qhhl$2@solani.org>
In reply to#671770
Hi,

Chris M. Thomasson can ask 100 more questions.
I will happily answer them. But maybe I should
make a Wiki to explain the ever same things:

 > But, I still don't know what you main goal is?
The goal is "Prolog inferencing"

 > It has textures to work with in the pipeline.
I don't need textures for "Prolog inferencing"

98 more questions to go, don't give up!

Bye

Mild Shock schrieb:
> Hi,
> 
> Tablets and phone are more annoying to
> use with WebGPU. The usual browsers don't
> have a Chrome DevTools panel integrated,
> 
> so that one could do JavaScript Debugging
> directly on the device. Instead one has to
> use a desktop machine, and connect the
> 
> device via UBS-C , and start a Chrome
> Browser there . And then start a Chrome
> DevTools panel alone, that is pair with
> 
> the device, via UBS-C cable. So this way
> I already see where it crashes on the
> tablets and phone:
> 
> await output.mapAsync(GPUMapMode.READ)
> Unhandled Promise Rejection: OperationError
> 
> The above is the error that one can re-produce
> already here with this test:
> 
> 11.4 Giga Lips with a Budget Laptop
> https://github.com/Jean-Luc-Picard-2021/gigabudget
> 
> Not sure what exactly happens. Maybe
> a form of timeout or device lost, that the
> primitive HTML / JavaScript doesn't handle
> 
> gracefully yet. Maybe redimensioning the
> test, so that it consumes less time would
> help. Who knows? Will see. For production
> 
> use of a GPU integration I have to anyway
> provide work slicing it seems.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Why does this Lama have a red pyjama.
>> Oh, its a baby Lama. Its still in the cradle
>> and needs some training:
>>
>> RedPajama-Data-v2
>> https://github.com/togethercomputer/RedPajama-Data
>>
>> But then Andrej Karpathy recently showed
>> GPT-2 training on rented GPUs for less
>> than 100 USD in less then 2 hours.
>>
>> So where do these grown up Lamas go.
>> Well Georgi Gerganov prefered C++/C
>> when he shouted Llama Llama Red Pyjama.
>>
>> But you also find WebLLM, wrapping the
>> underlying C++/C GPU interface via the
>> W3C standard WebGPU / WGSL, with JavaScript:
>>
>> In-Browser LLM Inference Engine
>> https://webllm.mlc.ai/
>>
>> My experience with WebLLM 6 months
>> ago on an iPad Pro 2024, still a little early
>> stage performance and robustness.
>>
>> But hey hardware of AI mobile iGPUs is
>> still evolving, and AI laptop, AI smartphones
>> and AI tablets, will soon feature Chinese
>>
>> hardware such some new Kirin AI in 2027.
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Remember when first all local AI was Python
>>> and PyTorch APIs. And then suddently people strated
>>> using bare metal C/C++ Code. Here is the story:
>>>
>>> How it started:
>>>
>>> GPT-J or GPT-J-6B is an open-source large
>>> language model (LLM) developed by EleutherAI
>>> in 2021. As the name suggests, it is a
>>> generative pre-trained transformer model
>>> designed to produce human-like text that
>>> continues from a prompt.
>>> https://www.eleuther.ai/
>>>
>>> How it was going [Georgi Gerganov]:
>>>
>>> So a few days later comes out the LLaMA, I do
>>> some calculations and I figure out “Okay, 65
>>> billion parameters. You probably need about
>>> 40 gigs of RAM, with 4-bit quantization. So
>>> this can run on a MacBook. Why not do it?”
>>>
>>> Why I was able to do it so quickly - basically,
>>> for all that I saw it’s pretty much GPT-J architecture
>>> with some modifications, like some extra memorization
>>> layers. It’s minor changes. Basically, again, the
>>> existing code for the GPT-J, I just simply
>>> modified it there, it happened pretty quickly.
>>> https://changelog.com/podcast/532
>>>
>>> Georgi Gerganov, Bulgarian, now with Hugging
>>> Face, ggml-cann also running on Chinese AI chips.
>>> ggml Manifesto https://github.com/ggml-org/ggml
>>>
>>> Bye
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]


#671786 — npm install webgpu [Google Dawn] (Was: Chris M. Thomasson can ask 100 more questions)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-02 03:01 +0200
Subjectnpm install webgpu [Google Dawn] (Was: Chris M. Thomasson can ask 100 more questions)
Message-ID<114m4sp$qi3v$1@solani.org>
In reply to#671785
Hi,

Ok, following the instructions here:

npm install webgpu
https://github.com/dawn-gpu/node-webgpu

I can now run webgpu also from CLI:

 >node.exe dogelog.mjs
Dogelog Spieler 2.2.5, Node, JavaScript 26.4.0
(c) 1985-2026, XLOG Technologies AG, Schweiz

?- ensure_loaded(library(edge/furryhaze)).
true.

?- between(1,3,_), time(expedite((between(1,100,_),
between(1,100,_), between(1,100,_)), [size(4096)])), fail.
% Zeit 1037.994 ms, GC 0.000 ms, Lips 111 k
% Zeit 1091.131 ms, GC 0.000 ms, Lips 106 k
% Zeit 1045.274 ms, GC 0.000 ms, Lips 110 k
fail.

Same benchmark result as in the browser.
Now I can rent a bigger GPU by the hour
and do some easy CLI testing.

LoL

Bye

Mild Shock schrieb:
> Hi,
> 
> Chris M. Thomasson can ask 100 more questions.
> I will happily answer them. But maybe I should
> make a Wiki to explain the ever same things:
> 
>  > But, I still don't know what you main goal is?
> The goal is "Prolog inferencing"
> 
>  > It has textures to work with in the pipeline.
> I don't need textures for "Prolog inferencing"
> 
> 98 more questions to go, don't give up!
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Tablets and phone are more annoying to
>> use with WebGPU. The usual browsers don't
>> have a Chrome DevTools panel integrated,
>>
>> so that one could do JavaScript Debugging
>> directly on the device. Instead one has to
>> use a desktop machine, and connect the
>>
>> device via UBS-C , and start a Chrome
>> Browser there . And then start a Chrome
>> DevTools panel alone, that is pair with
>>
>> the device, via UBS-C cable. So this way
>> I already see where it crashes on the
>> tablets and phone:
>>
>> await output.mapAsync(GPUMapMode.READ)
>> Unhandled Promise Rejection: OperationError
>>
>> The above is the error that one can re-produce
>> already here with this test:
>>
>> 11.4 Giga Lips with a Budget Laptop
>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>
>> Not sure what exactly happens. Maybe
>> a form of timeout or device lost, that the
>> primitive HTML / JavaScript doesn't handle
>>
>> gracefully yet. Maybe redimensioning the
>> test, so that it consumes less time would
>> help. Who knows? Will see. For production
>>
>> use of a GPU integration I have to anyway
>> provide work slicing it seems.
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Why does this Lama have a red pyjama.
>>> Oh, its a baby Lama. Its still in the cradle
>>> and needs some training:
>>>
>>> RedPajama-Data-v2
>>> https://github.com/togethercomputer/RedPajama-Data
>>>
>>> But then Andrej Karpathy recently showed
>>> GPT-2 training on rented GPUs for less
>>> than 100 USD in less then 2 hours.
>>>
>>> So where do these grown up Lamas go.
>>> Well Georgi Gerganov prefered C++/C
>>> when he shouted Llama Llama Red Pyjama.
>>>
>>> But you also find WebLLM, wrapping the
>>> underlying C++/C GPU interface via the
>>> W3C standard WebGPU / WGSL, with JavaScript:
>>>
>>> In-Browser LLM Inference Engine
>>> https://webllm.mlc.ai/
>>>
>>> My experience with WebLLM 6 months
>>> ago on an iPad Pro 2024, still a little early
>>> stage performance and robustness.
>>>
>>> But hey hardware of AI mobile iGPUs is
>>> still evolving, and AI laptop, AI smartphones
>>> and AI tablets, will soon feature Chinese
>>>
>>> hardware such some new Kirin AI in 2027.
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> Remember when first all local AI was Python
>>>> and PyTorch APIs. And then suddently people strated
>>>> using bare metal C/C++ Code. Here is the story:
>>>>
>>>> How it started:
>>>>
>>>> GPT-J or GPT-J-6B is an open-source large
>>>> language model (LLM) developed by EleutherAI
>>>> in 2021. As the name suggests, it is a
>>>> generative pre-trained transformer model
>>>> designed to produce human-like text that
>>>> continues from a prompt.
>>>> https://www.eleuther.ai/
>>>>
>>>> How it was going [Georgi Gerganov]:
>>>>
>>>> So a few days later comes out the LLaMA, I do
>>>> some calculations and I figure out “Okay, 65
>>>> billion parameters. You probably need about
>>>> 40 gigs of RAM, with 4-bit quantization. So
>>>> this can run on a MacBook. Why not do it?”
>>>>
>>>> Why I was able to do it so quickly - basically,
>>>> for all that I saw it’s pretty much GPT-J architecture
>>>> with some modifications, like some extra memorization
>>>> layers. It’s minor changes. Basically, again, the
>>>> existing code for the GPT-J, I just simply
>>>> modified it there, it happened pretty quickly.
>>>> https://changelog.com/podcast/532
>>>>
>>>> Georgi Gerganov, Bulgarian, now with Hugging
>>>> Face, ggml-cann also running on Chinese AI chips.
>>>> ggml Manifesto https://github.com/ggml-org/ggml
>>>>
>>>> Bye
>>>>
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]


#671808 — GPU elasticity was already invented in 2008 with CUDA (Re: npm install webgpu [Google Dawn])

FromMild Shock <janburse@fastmail.fm>
Date2026-08-02 23:59 +0200
SubjectGPU elasticity was already invented in 2008 with CUDA (Re: npm install webgpu [Google Dawn])
Message-ID<114oej8$rlg9$3@solani.org>
In reply to#671786
Hi,

Chris M. Thomasson schrieb:

 > Strive to never make a compute shader wait
 > on something, like an empty condition of a queue, stack.

You are such a moron. GPU elasticity was
already invented in 2008 with CUDA. I posted
this quote already:

"CUDA™ TEChNOLOGY UNLOCkS ThE
POWER OF TESLA MANY-CORE PROCESSORS

The CUDA C compiler simplifies many-core
programming by enabling code development
in a high-level language and optimizing code
to run on systems without knowledge of how

many cores are in the hardware. CUDA
applications automatically take advantage of
more cores or fewer cores in a system, so
they can scale from entry-level notebook

GPUs to high end GPUs in technical workstations
and further into racks of GPUs in data centers.
This allows developers to “code once” and
deploy on a range of systems, as well as scale

forward in time as future GPUs deliver more
performance per watt and more cores per
processor. The benefit for software users is
the opportunity to boost computing performance

simply by adding GPUs or using their existing GPUs in new ways"
https://www.nvidia.com/docs/IO/43395/NV_DS_Tesla_S1070_US_Jun08_NV_LR_Final.pdf

Today elasticity is on logical thread aka task level,
not only on "core" level or something. Don't know
exactly what CUDA did back them, maybe only

a submit elasticity, like a time sharing system. Today
you have quite some run elasticity on modern machines,
for your logical threads. Even in budget laptops

like a Ryzen AI 7 350 /w Radeon 850M.

Bye

P.S.: I can demostrate the elasticity, but I didn't
write the medium.com article yet.

Mild Shock schrieb:
> Hi,
> 
> Ok, following the instructions here:
> 
> npm install webgpu
> https://github.com/dawn-gpu/node-webgpu
> 
> I can now run webgpu also from CLI:
> 
>  >node.exe dogelog.mjs
> Dogelog Spieler 2.2.5, Node, JavaScript 26.4.0
> (c) 1985-2026, XLOG Technologies AG, Schweiz
> 
> ?- ensure_loaded(library(edge/furryhaze)).
> true.
> 
> ?- between(1,3,_), time(expedite((between(1,100,_),
> between(1,100,_), between(1,100,_)), [size(4096)])), fail.
> % Zeit 1037.994 ms, GC 0.000 ms, Lips 111 k
> % Zeit 1091.131 ms, GC 0.000 ms, Lips 106 k
> % Zeit 1045.274 ms, GC 0.000 ms, Lips 110 k
> fail.
> 
> Same benchmark result as in the browser.
> Now I can rent a bigger GPU by the hour
> and do some easy CLI testing.
> 
> LoL
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Chris M. Thomasson can ask 100 more questions.
>> I will happily answer them. But maybe I should
>> make a Wiki to explain the ever same things:
>>
>>  > But, I still don't know what you main goal is?
>> The goal is "Prolog inferencing"
>>
>>  > It has textures to work with in the pipeline.
>> I don't need textures for "Prolog inferencing"
>>
>> 98 more questions to go, don't give up!
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> Tablets and phone are more annoying to
>>> use with WebGPU. The usual browsers don't
>>> have a Chrome DevTools panel integrated,
>>>
>>> so that one could do JavaScript Debugging
>>> directly on the device. Instead one has to
>>> use a desktop machine, and connect the
>>>
>>> device via UBS-C , and start a Chrome
>>> Browser there . And then start a Chrome
>>> DevTools panel alone, that is pair with
>>>
>>> the device, via UBS-C cable. So this way
>>> I already see where it crashes on the
>>> tablets and phone:
>>>
>>> await output.mapAsync(GPUMapMode.READ)
>>> Unhandled Promise Rejection: OperationError
>>>
>>> The above is the error that one can re-produce
>>> already here with this test:
>>>
>>> 11.4 Giga Lips with a Budget Laptop
>>> https://github.com/Jean-Luc-Picard-2021/gigabudget
>>>
>>> Not sure what exactly happens. Maybe
>>> a form of timeout or device lost, that the
>>> primitive HTML / JavaScript doesn't handle
>>>
>>> gracefully yet. Maybe redimensioning the
>>> test, so that it consumes less time would
>>> help. Who knows? Will see. For production
>>>
>>> use of a GPU integration I have to anyway
>>> provide work slicing it seems.
>>>
>>> Bye
>>>
>>> Mild Shock schrieb:
>>>> Hi,
>>>>
>>>> Why does this Lama have a red pyjama.
>>>> Oh, its a baby Lama. Its still in the cradle
>>>> and needs some training:
>>>>
>>>> RedPajama-Data-v2
>>>> https://github.com/togethercomputer/RedPajama-Data
>>>>
>>>> But then Andrej Karpathy recently showed
>>>> GPT-2 training on rented GPUs for less
>>>> than 100 USD in less then 2 hours.
>>>>
>>>> So where do these grown up Lamas go.
>>>> Well Georgi Gerganov prefered C++/C
>>>> when he shouted Llama Llama Red Pyjama.
>>>>
>>>> But you also find WebLLM, wrapping the
>>>> underlying C++/C GPU interface via the
>>>> W3C standard WebGPU / WGSL, with JavaScript:
>>>>
>>>> In-Browser LLM Inference Engine
>>>> https://webllm.mlc.ai/
>>>>
>>>> My experience with WebLLM 6 months
>>>> ago on an iPad Pro 2024, still a little early
>>>> stage performance and robustness.
>>>>
>>>> But hey hardware of AI mobile iGPUs is
>>>> still evolving, and AI laptop, AI smartphones
>>>> and AI tablets, will soon feature Chinese
>>>>
>>>> hardware such some new Kirin AI in 2027.
>>>>
>>>> Bye
>>>>
>>>> Mild Shock schrieb:
>>>>> Hi,
>>>>>
>>>>> Remember when first all local AI was Python
>>>>> and PyTorch APIs. And then suddently people strated
>>>>> using bare metal C/C++ Code. Here is the story:
>>>>>
>>>>> How it started:
>>>>>
>>>>> GPT-J or GPT-J-6B is an open-source large
>>>>> language model (LLM) developed by EleutherAI
>>>>> in 2021. As the name suggests, it is a
>>>>> generative pre-trained transformer model
>>>>> designed to produce human-like text that
>>>>> continues from a prompt.
>>>>> https://www.eleuther.ai/
>>>>>
>>>>> How it was going [Georgi Gerganov]:
>>>>>
>>>>> So a few days later comes out the LLaMA, I do
>>>>> some calculations and I figure out “Okay, 65
>>>>> billion parameters. You probably need about
>>>>> 40 gigs of RAM, with 4-bit quantization. So
>>>>> this can run on a MacBook. Why not do it?”
>>>>>
>>>>> Why I was able to do it so quickly - basically,
>>>>> for all that I saw it’s pretty much GPT-J architecture
>>>>> with some modifications, like some extra memorization
>>>>> layers. It’s minor changes. Basically, again, the
>>>>> existing code for the GPT-J, I just simply
>>>>> modified it there, it happened pretty quickly.
>>>>> https://changelog.com/podcast/532
>>>>>
>>>>> Georgi Gerganov, Bulgarian, now with Hugging
>>>>> Face, ggml-cann also running on Chinese AI chips.
>>>>> ggml Manifesto https://github.com/ggml-org/ggml
>>>>>
>>>>> Bye
>>>>>
>>>>
>>>
>>
> 

[toc] | [prev] | [next] | [standalone]


#671793 — Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)

FromJohann 'Myrkraverk' Oskarsson <johann@myrkraverk.invalid>
Date2026-08-03 00:34 +0800
SubjectRe: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)
Message-ID<ekKbS.129884$9jNc.102967@fx16.ams4>
In reply to#671785
On 02/08/2026 8:47 AM, Mild Shock wrote:
> Hi,
> 
> Chris M. Thomasson can ask 100 more questions.
> I will happily answer them. But maybe I should
> make a Wiki to explain the ever same things:
> 
>  > But, I still don't know what you main goal is?
> The goal is "Prolog inferencing"

Don't worry about it.  There are several regulars here
who
     don't
           understand

that programming can be done for fun.

> 
>  > It has textures to work with in the pipeline.
> I don't need textures for "Prolog inferencing"
> 
> 98 more questions to go, don't give up!

Here in sci.math, as everyone knows, I'm gearing up for
/linear algebra/ for fun.  Still waiting for DVDs because
I'm not in a hurry.  The book /Linear Algebra Done Right/
is interesting, and I've yet to go through the other rec-
commendations.[1]

I'm curious if you've ever thought of doing OpenGL with Prolog?

Does that even work?


[1] I have no idea how this word is supposed to be hyphenated,
     I just do it anyway, because I'm not an LLM.
> 
> Bye

Take care!

-- 
Johann | email: invalid -> com | http://www.myrkraverk.com/blog/
I'm not from the Internet, I just work there. | via Easynews.com

[toc] | [prev] | [next] | [standalone]


#671794 — Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)

FromRoss Finlayson <ross.a.finlayson@gmail.com>
Date2026-08-02 10:41 -0700
SubjectRe: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)
Message-ID<H-mcnW2o5ZLcHPL3nZ2dnZfqn_idnZ2d@giganews.com>
In reply to#671793
On 08/02/2026 09:34 AM, Johann 'Myrkraverk' Oskarsson wrote:
> On 02/08/2026 8:47 AM, Mild Shock wrote:
>> Hi,
>>
>> Chris M. Thomasson can ask 100 more questions.
>> I will happily answer them. But maybe I should
>> make a Wiki to explain the ever same things:
>>
>>  > But, I still don't know what you main goal is?
>> The goal is "Prolog inferencing"
>
> Don't worry about it.  There are several regulars here
> who
>      don't
>            understand
>
> that programming can be done for fun.
>
>>
>>  > It has textures to work with in the pipeline.
>> I don't need textures for "Prolog inferencing"
>>
>> 98 more questions to go, don't give up!
>
> Here in sci.math, as everyone knows, I'm gearing up for
> /linear algebra/ for fun.  Still waiting for DVDs because
> I'm not in a hurry.  The book /Linear Algebra Done Right/
> is interesting, and I've yet to go through the other rec-
> commendations.[1]
>
> I'm curious if you've ever thought of doing OpenGL with Prolog?
>
> Does that even work?
>
>
> [1] I have no idea how this word is supposed to be hyphenated,
>      I just do it anyway, because I'm not an LLM.
>>
>> Bye
>
> Take care!
>

You might have good luck looking up reputable university programs
and seeing what textbooks they require, these days.

Or, you know, just buy old ones when the library retires
the old good ones.

How about Householder's "The Theory of Matrices in Numerical Analysis".

Linear independence and linear spaces inevitably
get associated with vector spaces. There are much
simpler accounts though of reflections and rotations
about the determinantal and the singular and the decompositions
and the forms and the echelon forms and reduction with regards
to things like cumulants and orthogonants and the matroids,
vis-a-vis usual closed categories and so on.

The cumulants and orthogonants and so on are lesser-served
accounts of the earlier 20'th century, and determinantal analysis, while
the matroids are the a bit more obscure accounts of geometrizations with
regards to matrices.

What "linear" even is is usually enough "linear is linear".
Generally considered "ordinary" if through substitution.


I'm an anti-reductionist, yet though reduction is one
of the most usual results in closed categories, the
methods and techniques, point being closed categories
aren't allowed to close themselves, only being found so.




[toc] | [prev] | [next] | [standalone]


#671796 — Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)

FromRoss Finlayson <ross.a.finlayson@gmail.com>
Date2026-08-02 11:13 -0700
SubjectRe: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)
Message-ID<VySdnV33ZYBHFfL3nZ2dnZfqn_SdnZ2d@giganews.com>
In reply to#671794
On 08/02/2026 10:41 AM, Ross Finlayson wrote:
> On 08/02/2026 09:34 AM, Johann 'Myrkraverk' Oskarsson wrote:
>> On 02/08/2026 8:47 AM, Mild Shock wrote:
>>> Hi,
>>>
>>> Chris M. Thomasson can ask 100 more questions.
>>> I will happily answer them. But maybe I should
>>> make a Wiki to explain the ever same things:
>>>
>>>  > But, I still don't know what you main goal is?
>>> The goal is "Prolog inferencing"
>>
>> Don't worry about it.  There are several regulars here
>> who
>>      don't
>>            understand
>>
>> that programming can be done for fun.
>>
>>>
>>>  > It has textures to work with in the pipeline.
>>> I don't need textures for "Prolog inferencing"
>>>
>>> 98 more questions to go, don't give up!
>>
>> Here in sci.math, as everyone knows, I'm gearing up for
>> /linear algebra/ for fun.  Still waiting for DVDs because
>> I'm not in a hurry.  The book /Linear Algebra Done Right/
>> is interesting, and I've yet to go through the other rec-
>> commendations.[1]
>>
>> I'm curious if you've ever thought of doing OpenGL with Prolog?
>>
>> Does that even work?
>>
>>
>> [1] I have no idea how this word is supposed to be hyphenated,
>>      I just do it anyway, because I'm not an LLM.
>>>
>>> Bye
>>
>> Take care!
>>
>
> You might have good luck looking up reputable university programs
> and seeing what textbooks they require, these days.
>
> Or, you know, just buy old ones when the library retires
> the old good ones.
>
> How about Householder's "The Theory of Matrices in Numerical Analysis".
>
> Linear independence and linear spaces inevitably
> get associated with vector spaces. There are much
> simpler accounts though of reflections and rotations
> about the determinantal and the singular and the decompositions
> and the forms and the echelon forms and reduction with regards
> to things like cumulants and orthogonants and the matroids,
> vis-a-vis usual closed categories and so on.
>
> The cumulants and orthogonants and so on are lesser-served
> accounts of the earlier 20'th century, and determinantal analysis, while
> the matroids are the a bit more obscure accounts of geometrizations with
> regards to matrices.
>
> What "linear" even is is usually enough "linear is linear".
> Generally considered "ordinary" if through substitution.
>
>
> I'm an anti-reductionist, yet though reduction is one
> of the most usual results in closed categories, the
> methods and techniques, point being closed categories
> aren't allowed to close themselves, only being found so.
>
>
>
>
>

Sometimes "linear independence" is better read as "linear dependence",
this is because words like "abstract" and "general" and "closed" and
"regular" and "ordinary" have inverses, matters of perspective and
projection, then about the difference from the "non", the "super",
for example the "classical".

"Truth is regular. Geometry is motion."

[toc] | [prev] | [next] | [standalone]


#671798 — Re: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)

From"Chris M. Thomasson" <chris.m.thomasson.1@gmail.com>
Date2026-08-02 12:42 -0700
SubjectRe: Chris M. Thomasson can ask 100 more questions (Re: Tablet and phone UBS-C remote debugging)
Message-ID<114o6ii$ohrk$1@dont-email.me>
In reply to#671785
On 8/1/2026 5:47 PM, Mild Shock wrote:
> Hi,
> 
> Chris M. Thomasson can ask 100 more questions.
> I will happily answer them. But maybe I should
> make a Wiki to explain the ever same things:
> 
>  > But, I still don't know what you main goal is?
> The goal is "Prolog inferencing"
> 
>  > It has textures to work with in the pipeline.
> I don't need textures for "Prolog inferencing"
> 
> 98 more questions to go, don't give up!
[...]

Fwiw, I have several compute shaders that do what I want. Mainly 
building vector fields, etc.... And yes I use textures for some input 
and output, uniforms mainly for the settings, etc. Just, make sure to 
code things up to a point where your compute shader never needs to wait 
for something... Think of striving for wait-free algorithms.

For instance, this is 100% wait free.

void add_hit(ct_plane2d plane, vec2 p, vec3 weight)
{
     vec2 uv = ct_plane2d_unproject(plane, p);
     ivec2 px = ivec2(uv * u_resolution);

     if (px.x >= 0 && px.x < int(u_resolution.x) &&
         px.y >= 0 && px.y < int(u_resolution.y))
     {
         imageAtomicAdd(accum_r,    px, weight.r);
         imageAtomicAdd(accum_g,    px, weight.g);
         imageAtomicAdd(accum_b,    px, weight.b);
         imageAtomicAdd(accum_hits, px, 1.0f);
     }
}


Notice how I separated my accumulation buffer into different textures?

layout(binding = 0, r32f) uniform coherent image2D accum_r;
layout(binding = 1, r32f) uniform coherent image2D accum_g;
layout(binding = 2, r32f) uniform coherent image2D accum_b;
layout(binding = 3, r32f) uniform coherent image2D accum_hits;  // alpha 
/ hit counter

Works great and runs really fast.

[toc] | [prev] | [next] | [standalone]


#671801 — You posted that already, but you didn't listen [I NEED BOUNDED QUEUES] (Was: Chris M. Thomasson can ask 100 more questions)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-02 23:09 +0200
SubjectYou posted that already, but you didn't listen [I NEED BOUNDED QUEUES] (Was: Chris M. Thomasson can ask 100 more questions)
Message-ID<114obm9$rk0b$1@solani.org>
In reply to#671798
Hi,

I assure you I have like 3-4 times already
communicated to you that my requirements are
bounded queues. And not the ideally unbounded queues
that you are using, i.e. imageAtomicAdd.

Just check the postings in this forum. I have
like 3-4 times already specified that I need
bounded queues.

 > Works great and runs really fast.

You repeating yourself. Whats the motivation
of this spamming. I mean I can officially acknowledge
here that I have seen your imageAtomicAdd code

already. I also responded back then that I
have a Queue prototype that exactly uses that.
But it doesn't work for my purpose because I need:

- bounded queues that can block
- sizes are typically like 4-32 elements
- blocking is not done in GPU
- blocking is done in Hack
- Hack can do work stealing etc..

Because Hack can do a lot of tricks, you shouldn't
worry at all. Also spinning with backoff etc..
could be part of the picture, just check out:

Parallel Programming, Spring 2019, Lecture 16+1:
Spinlocks, Deadlocks, Semaphores
https://spcl.inf.ethz.ch/Teaching/2020-pp/lectures/PP-l17-BeyondLocks.pdf

So just let me do my research, and refrain from
spamming me with always the same nonsense. Better
listen. I assure you I have like 3-4 times already

communicated to you that my requirements are
bounded queues. And not the ideally unbounded queues
that you are using., i.e. imageAtomicAdd.

Just check the postings in this forum. I have
like 3-4 times already specified that I need
bounded queues.

Bye


Chris M. Thomasson schrieb:
> On 8/1/2026 5:47 PM, Mild Shock wrote:
>> Hi,
>>
>> Chris M. Thomasson can ask 100 more questions.
>> I will happily answer them. But maybe I should
>> make a Wiki to explain the ever same things:
>>
>>  > But, I still don't know what you main goal is?
>> The goal is "Prolog inferencing"
>>
>>  > It has textures to work with in the pipeline.
>> I don't need textures for "Prolog inferencing"
>>
>> 98 more questions to go, don't give up!
> [...]
> 
> Fwiw, I have several compute shaders that do what I want. Mainly 
> building vector fields, etc.... And yes I use textures for some input 
> and output, uniforms mainly for the settings, etc. Just, make sure to 
> code things up to a point where your compute shader never needs to wait 
> for something... Think of striving for wait-free algorithms.
> 
> For instance, this is 100% wait free.
> 
> void add_hit(ct_plane2d plane, vec2 p, vec3 weight)
> {
>      vec2 uv = ct_plane2d_unproject(plane, p);
>      ivec2 px = ivec2(uv * u_resolution);
> 
>      if (px.x >= 0 && px.x < int(u_resolution.x) &&
>          px.y >= 0 && px.y < int(u_resolution.y))
>      {
>          imageAtomicAdd(accum_r,    px, weight.r);
>          imageAtomicAdd(accum_g,    px, weight.g);
>          imageAtomicAdd(accum_b,    px, weight.b);
>          imageAtomicAdd(accum_hits, px, 1.0f);
>      }
> }
> 
> 
> Notice how I separated my accumulation buffer into different textures?
> 
> layout(binding = 0, r32f) uniform coherent image2D accum_r;
> layout(binding = 1, r32f) uniform coherent image2D accum_g;
> layout(binding = 2, r32f) uniform coherent image2D accum_b;
> layout(binding = 3, r32f) uniform coherent image2D accum_hits;  // alpha 
> / hit counter
> 
> Works great and runs really fast.

[toc] | [prev] | [next] | [standalone]


#671802 — Summary of 100 questions Chris M. Thomasson can ask (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES])

FromMild Shock <janburse@fastmail.fm>
Date2026-08-02 23:17 +0200
SubjectSummary of 100 questions Chris M. Thomasson can ask (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES])
Message-ID<114oc4r$rkbc$1@solani.org>
In reply to#671801
Hi,

Chris M. Thomasson can ask 100 more questions.
I will happily answer them. But maybe I should
make a Wiki to explain the ever same things:

 > But, I still don't know what you main goal is?
The goal is "Prolog inferencing"

 > It has textures to work with in the pipeline.
I don't need textures for "Prolog inferencing"

 > You seem to need queues, why not "imageAtomicAdd"
I don't need ideally unbouded queues from WebGL

 > But the "imageAtomicAdd" are wait-free
I don't need wait-free queues, my queues should block

Hard to swallow, isn't it? Not my problem, its yours!

97 more questions to go, don't give up!

Bye

Mild Shock schrieb:
> Hi,
> 
> I assure you I have like 3-4 times already
> communicated to you that my requirements are
> bounded queues. And not the ideally unbounded queues
> that you are using, i.e. imageAtomicAdd.
> 
> Just check the postings in this forum. I have
> like 3-4 times already specified that I need
> bounded queues.
> 
>  > Works great and runs really fast.
> 
> You repeating yourself. Whats the motivation
> of this spamming. I mean I can officially acknowledge
> here that I have seen your imageAtomicAdd code
> 
> already. I also responded back then that I
> have a Queue prototype that exactly uses that.
> But it doesn't work for my purpose because I need:
> 
> - bounded queues that can block
> - sizes are typically like 4-32 elements
> - blocking is not done in GPU
> - blocking is done in Hack
> - Hack can do work stealing etc..
> 
> Because Hack can do a lot of tricks, you shouldn't
> worry at all. Also spinning with backoff etc..
> could be part of the picture, just check out:
> 
> Parallel Programming, Spring 2019, Lecture 16+1:
> Spinlocks, Deadlocks, Semaphores
> https://spcl.inf.ethz.ch/Teaching/2020-pp/lectures/PP-l17-BeyondLocks.pdf
> 
> So just let me do my research, and refrain from
> spamming me with always the same nonsense. Better
> listen. I assure you I have like 3-4 times already
> 
> communicated to you that my requirements are
> bounded queues. And not the ideally unbounded queues
> that you are using., i.e. imageAtomicAdd.
> 
> Just check the postings in this forum. I have
> like 3-4 times already specified that I need
> bounded queues.
> 
> Bye
> 
> 
> Chris M. Thomasson schrieb:
>> On 8/1/2026 5:47 PM, Mild Shock wrote:
>>> Hi,
>>>
>>> Chris M. Thomasson can ask 100 more questions.
>>> I will happily answer them. But maybe I should
>>> make a Wiki to explain the ever same things:
>>>
>>>  > But, I still don't know what you main goal is?
>>> The goal is "Prolog inferencing"
>>>
>>>  > It has textures to work with in the pipeline.
>>> I don't need textures for "Prolog inferencing"
>>>
>>> 98 more questions to go, don't give up!
>> [...]
>>
>> Fwiw, I have several compute shaders that do what I want. Mainly 
>> building vector fields, etc.... And yes I use textures for some input 
>> and output, uniforms mainly for the settings, etc. Just, make sure to 
>> code things up to a point where your compute shader never needs to 
>> wait for something... Think of striving for wait-free algorithms.
>>
>> For instance, this is 100% wait free.
>>
>> void add_hit(ct_plane2d plane, vec2 p, vec3 weight)
>> {
>>      vec2 uv = ct_plane2d_unproject(plane, p);
>>      ivec2 px = ivec2(uv * u_resolution);
>>
>>      if (px.x >= 0 && px.x < int(u_resolution.x) &&
>>          px.y >= 0 && px.y < int(u_resolution.y))
>>      {
>>          imageAtomicAdd(accum_r,    px, weight.r);
>>          imageAtomicAdd(accum_g,    px, weight.g);
>>          imageAtomicAdd(accum_b,    px, weight.b);
>>          imageAtomicAdd(accum_hits, px, 1.0f);
>>      }
>> }
>>
>>
>> Notice how I separated my accumulation buffer into different textures?
>>
>> layout(binding = 0, r32f) uniform coherent image2D accum_r;
>> layout(binding = 1, r32f) uniform coherent image2D accum_g;
>> layout(binding = 2, r32f) uniform coherent image2D accum_b;
>> layout(binding = 3, r32f) uniform coherent image2D accum_hits;  // 
>> alpha / hit counter
>>
>> Works great and runs really fast.
> 

[toc] | [prev] | [next] | [standalone]


#671803 — Summary of 100 questions Chris M. Thomasson can ask (Re: You posted that already, but you didn't listen)

FromMild Shock <janburse@fastmail.fm>
Date2026-08-02 23:20 +0200
SubjectSummary of 100 questions Chris M. Thomasson can ask (Re: You posted that already, but you didn't listen)
Message-ID<114ocb4$rkbc$2@solani.org>
In reply to#671801
Hi,

Chris M. Thomasson can ask 100 more questions.
I will happily answer them. But maybe I should
make a Wiki to explain the ever same things:

 > But, I still don't know what you main goal is?
The goal is "Prolog inferencing"

 > It has textures to work with in the pipeline.
I don't need textures for "Prolog inferencing"

 > You seem to need queues, why not "imageAtomicAdd"
I don't need ideally unbouded queues from WebGL

 > But the "imageAtomicAdd" are wait-free
I don't need wait-free queues, my queues should block

Hard to swallow, isn't it? Not my problem, its yours!

96 more questions to go, don't give up!

Bye

Mild Shock schrieb:
> Hi,
> 
> I assure you I have like 3-4 times already
> communicated to you that my requirements are
> bounded queues. And not the ideally unbounded queues
> that you are using, i.e. imageAtomicAdd.
> 
> Just check the postings in this forum. I have
> like 3-4 times already specified that I need
> bounded queues.
> 
>  > Works great and runs really fast.
> 
> You repeating yourself. Whats the motivation
> of this spamming. I mean I can officially acknowledge
> here that I have seen your imageAtomicAdd code
> 
> already. I also responded back then that I
> have a Queue prototype that exactly uses that.
> But it doesn't work for my purpose because I need:
> 
> - bounded queues that can block
> - sizes are typically like 4-32 elements
> - blocking is not done in GPU
> - blocking is done in Hack
> - Hack can do work stealing etc..
> 
> Because Hack can do a lot of tricks, you shouldn't
> worry at all. Also spinning with backoff etc..
> could be part of the picture, just check out:
> 
> Parallel Programming, Spring 2019, Lecture 16+1:
> Spinlocks, Deadlocks, Semaphores
> https://spcl.inf.ethz.ch/Teaching/2020-pp/lectures/PP-l17-BeyondLocks.pdf
> 
> So just let me do my research, and refrain from
> spamming me with always the same nonsense. Better
> listen. I assure you I have like 3-4 times already
> 
> communicated to you that my requirements are
> bounded queues. And not the ideally unbounded queues
> that you are using., i.e. imageAtomicAdd.
> 
> Just check the postings in this forum. I have
> like 3-4 times already specified that I need
> bounded queues.
> 
> Bye
> 
> 
> Chris M. Thomasson schrieb:
>> On 8/1/2026 5:47 PM, Mild Shock wrote:
>>> Hi,
>>>
>>> Chris M. Thomasson can ask 100 more questions.
>>> I will happily answer them. But maybe I should
>>> make a Wiki to explain the ever same things:
>>>
>>>  > But, I still don't know what you main goal is?
>>> The goal is "Prolog inferencing"
>>>
>>>  > It has textures to work with in the pipeline.
>>> I don't need textures for "Prolog inferencing"
>>>
>>> 98 more questions to go, don't give up!
>> [...]
>>
>> Fwiw, I have several compute shaders that do what I want. Mainly 
>> building vector fields, etc.... And yes I use textures for some input 
>> and output, uniforms mainly for the settings, etc. Just, make sure to 
>> code things up to a point where your compute shader never needs to 
>> wait for something... Think of striving for wait-free algorithms.
>>
>> For instance, this is 100% wait free.
>>
>> void add_hit(ct_plane2d plane, vec2 p, vec3 weight)
>> {
>>      vec2 uv = ct_plane2d_unproject(plane, p);
>>      ivec2 px = ivec2(uv * u_resolution);
>>
>>      if (px.x >= 0 && px.x < int(u_resolution.x) &&
>>          px.y >= 0 && px.y < int(u_resolution.y))
>>      {
>>          imageAtomicAdd(accum_r,    px, weight.r);
>>          imageAtomicAdd(accum_g,    px, weight.g);
>>          imageAtomicAdd(accum_b,    px, weight.b);
>>          imageAtomicAdd(accum_hits, px, 1.0f);
>>      }
>> }
>>
>>
>> Notice how I separated my accumulation buffer into different textures?
>>
>> layout(binding = 0, r32f) uniform coherent image2D accum_r;
>> layout(binding = 1, r32f) uniform coherent image2D accum_g;
>> layout(binding = 2, r32f) uniform coherent image2D accum_b;
>> layout(binding = 3, r32f) uniform coherent image2D accum_hits;  // 
>> alpha / hit counter
>>
>> Works great and runs really fast.
> 

[toc] | [prev] | [next] | [standalone]


#671824 — Re: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES] (Was: Chris M. Thomasson can ask 100 more questions)

From"Chris M. Thomasson" <chris.m.thomasson.1@gmail.com>
Date2026-08-03 12:55 -0700
SubjectRe: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES] (Was: Chris M. Thomasson can ask 100 more questions)
Message-ID<114qrn5$1ju8n$2@dont-email.me>
In reply to#671801
On 8/2/2026 2:09 PM, Mild Shock wrote:
[...]

Good bye.

[toc] | [prev] | [next] | [standalone]


Page 7 of 9 — ← Prev page 1 2 3 4 5 6 [7] 8 9  Next page →

Back to top | Article view | sci.physics.relativity


csiph-web