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]

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
        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
    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
    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
        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

Page 7 of 7 — ← Prev page 1 2 3 4 5 6 [7]

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

On 8/2/2026 2:09 PM, Mild Shock wrote:
[...]

Good bye.

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

#671826 — Liar and spammer (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES])

Hi,

You give up, the rat your are.

Liar and spammer.

Bye

Chris M. Thomasson schrieb:
> On 8/2/2026 2:09 PM, Mild Shock wrote:
> [...]
> 
> Good bye.
> 

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

#671827 — Re: Liar and spammer (Was: You posted that already, but you didn't listen [I NEED BOUNDED QUEUES])

Mild Shock wrote:

> Hi,
> 
> You give up, the rat your are.
> 
> Liar and spammer.

you are so stupid you cant even fit a curve mathematically

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

#671895 — Synthetic Multilanguage Autoformalization Dataset [Informath project] (Re: Lamas in a cradle and Lamas on the edge [Red Pyjama] )

Hi,

Why is nobody mentioning Agda here. It has
beautiful dependent types, and tactics are
just programs. Poor Henk Barendregt, not

everybody likes dependent types it seems:

Are we stuck with Lean?
https://mathoverflow.net/q/513742/

Does Depependent types require proof objects,
which waste large amounts of memory. Well,
if you are not good in erasing them.

But is there a Red Pyjama for Proof Assistants,
the baby cradle where LLMs can learn proof
assistant lingua and strategies. It seems

yes, synthetic data corpuses to the rescue:

We address this gap by introducing SMAD
(Synthetic Multilanguage Autoformalization
Dataset), a 400K 4-to-3 parallel corpus
covering four formal languages (Dedukti,
Agda, Coq, Lean) and three natural languages (
English, French, Swedish), generated via
the Informath project.
https://github.com/GrammaticalFramework/informath

But the corpus could be an accident, maybe rather
a toy from the https://www.grammaticalframework.org/
folks, will this have an impact?

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]

#672060 — 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] )

Hi,

Years ago Sam Altman said to have no idea how
to generate revenue, but when the generally
intelligent system is in place, he might ask it.

Some schools approach the “generality” from
a totally wrong perspective. Take the EyeProlog
Pseudo Scientism here:

The Art of EyeProlog
https://eyereasoner.github.io/eyeprolog/the-art-of-eyeprolog

It is the same nonsense like constraint propagation,
the idea here is to evolve better software, that it
has as a main component refinement:

Start -> Algo1 -> Algo2 -> Algo3 -> Algo4 ...

But EyeProlog itself is an example of not using
this refinement. Like dropping the classical
WAM architecture, and back to YieldProlog somehow.

What if the world ticks like this
when it come to generality:

        /-> Algo1
       /--> Algo2
Start ---> Algo3
       \--> Algo4
        \-> ...

Innovation requires to start from scratch.
I think this little booklet, recommended by
Ernst Specker, Proofs from THE BOOK is a

book of mathematical proofs by Martin Aigner
and Günter M. Ziegler, first published in 1998.
Just wants to teach us about this bifurcation:

Chapter 1: Six proofs of the infinity of
the primes, including Euclid's and Furstenberg's.
https://en.wikipedia.org/wiki/Proofs_from_THE_BOOK

Yeah, lets aim for surprises by
generative AI, not refinement.

Bye

See also:

Sam Altman on his Business Model
https://www.youtube.com/shorts/pLnyjxgFxew

Mild Shock schrieb:
> Hi,
> 
> Why is nobody mentioning Agda here. It has
> beautiful dependent types, and tactics are
> just programs. Poor Henk Barendregt, not
> 
> everybody likes dependent types it seems:
> 
> Are we stuck with Lean?
> https://mathoverflow.net/q/513742/
> 
> Does Depependent types require proof objects,
> which waste large amounts of memory. Well,
> if you are not good in erasing them.
> 
> But is there a Red Pyjama for Proof Assistants,
> the baby cradle where LLMs can learn proof
> assistant lingua and strategies. It seems
> 
> yes, synthetic data corpuses to the rescue:
> 
> We address this gap by introducing SMAD
> (Synthetic Multilanguage Autoformalization
> Dataset), a 400K 4-to-3 parallel corpus
> covering four formal languages (Dedukti,
> Agda, Coq, Lean) and three natural languages (
> English, French, Swedish), generated via
> the Informath project.
> https://github.com/GrammaticalFramework/informath
> 
> But the corpus could be an accident, maybe rather
> a toy from the https://www.grammaticalframework.org/
> folks, will this have an impact?
> 
> 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]

#672066 — Everybody does eat and sleep [The SK hynix Story] (Re: Six Proofs and Generally Inteligent Systems [EyeProlog Pseudo Scientism])

Hi,

Every does eat and sleep. Thats not,
don't give up and restart:

Cite 100 collegues, cite 100 papers, and
do 100 Python snippets. Thats only warm-up!
About - Hi, I’m Philip Zucker!
https://www.philipzucker.com/about/

One the other hand, that here is true
don't give up and restart:

Invent a dozen acronyms HMB2, HBM2E, TC-NCF,
MR-UF, MUF, MR-MUF and try them all.
How SK hynix Won the AI Memory Race
https://www.youtube.com/watch?v=Cg5tAujp6Go

Bye

Mild Shock schrieb:
> Hi,
> 
> Years ago Sam Altman said to have no idea how
> to generate revenue, but when the generally
> intelligent system is in place, he might ask it.
> 
> Some schools approach the “generality” from
> a totally wrong perspective. Take the EyeProlog
> Pseudo Scientism here:
> 
> The Art of EyeProlog
> https://eyereasoner.github.io/eyeprolog/the-art-of-eyeprolog
> 
> It is the same nonsense like constraint propagation,
> the idea here is to evolve better software, that it
> has as a main component refinement:
> 
> Start -> Algo1 -> Algo2 -> Algo3 -> Algo4 ...
> 
> But EyeProlog itself is an example of not using
> this refinement. Like dropping the classical
> WAM architecture, and back to YieldProlog somehow.
> 
> What if the world ticks like this
> when it come to generality:
> 
>         /-> Algo1
>        /--> Algo2
> Start ---> Algo3
>        \--> Algo4
>         \-> ...
> 
> Innovation requires to start from scratch.
> I think this little booklet, recommended by
> Ernst Specker, Proofs from THE BOOK is a
> 
> book of mathematical proofs by Martin Aigner
> and Günter M. Ziegler, first published in 1998.
> Just wants to teach us about this bifurcation:
> 
> Chapter 1: Six proofs of the infinity of
> the primes, including Euclid's and Furstenberg's.
> https://en.wikipedia.org/wiki/Proofs_from_THE_BOOK
> 
> Yeah, lets aim for surprises by
> generative AI, not refinement.
> 
> Bye
> 
> See also:
> 
> Sam Altman on his Business Model
> https://www.youtube.com/shorts/pLnyjxgFxew
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Why is nobody mentioning Agda here. It has
>> beautiful dependent types, and tactics are
>> just programs. Poor Henk Barendregt, not
>>
>> everybody likes dependent types it seems:
>>
>> Are we stuck with Lean?
>> https://mathoverflow.net/q/513742/
>>
>> Does Depependent types require proof objects,
>> which waste large amounts of memory. Well,
>> if you are not good in erasing them.
>>
>> But is there a Red Pyjama for Proof Assistants,
>> the baby cradle where LLMs can learn proof
>> assistant lingua and strategies. It seems
>>
>> yes, synthetic data corpuses to the rescue:
>>
>> We address this gap by introducing SMAD
>> (Synthetic Multilanguage Autoformalization
>> Dataset), a 400K 4-to-3 parallel corpus
>> covering four formal languages (Dedukti,
>> Agda, Coq, Lean) and three natural languages (
>> English, French, Swedish), generated via
>> the Informath project.
>> https://github.com/GrammaticalFramework/informath
>>
>> But the corpus could be an accident, maybe rather
>> a toy from the https://www.grammaticalframework.org/
>> folks, will this have an impact?
>>
>> 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]

#671804 — Even send_color and recv_color can block [Cerebras Waver] Re: The Wuhan Virus that destroyed Python [ggml Manifesto]

Hi,

If only the fucking moron Chris M. Thomasson would
stop spamming his nonsense, he doesn't listen at
all. Problem, he cannot read, he knows nothing.

Its very common that compute shaders can block,
when they are used for General Purpose computation
on GPUs (GPGPU). If only he would pull out his

finger from his asshole, and stop thinking in is
WebGL legacy code stash nonsense. Even the
Cerebras Waver has blocking:

"Cerebras Software Language (CSL), send_color
and recv_color are parameters passed to tile
programs to manage data routing and virtual
channels (called colors) across processing
elements (PEs) on the wafer

Yes, both send and receive operations can block
on a Cerebras Processing Element (PE), primarily
due to the system's hardware-enforced backpressure
mechanism. Because the Cerebras Wafer-Scale Engine
(WSE) relies on a fine-grained,

dataflow-driven architecture, blocking prevents
data loss when hardware resources are
fully saturated."

Blocking and Unblocking
https://sdk.cerebras.ai/computing-with-cerebras#blocking-and-unblocking

Chris M. Thomasson is an annoyance and an idiot.
He is a total waste of time. And represents those
people who cannot use their brain.

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]

#671869 — GPU Elasticity: Collective Communications Libraries (Was: The Wuhan Virus that destroyed Python [ggml Manifesto])

Hi,

How it started, NVIDIA being cool:

NCCL provides routines such as all-gather,
all-reduce, broadcast, reduce, reduce-scatter,
and point-to-point send and receive. These
routines are optimized to achieve high
bandwidth and low latency over PCIe,
NVIDIA NVLink™, and other high-speed
interconnects within a node and over
NVIDIA networking across nodes.
https://developer.nvidia.com/nccl

How its going, vLLM trying to be cool:

[RFC]: Native Weight Syncing APIs
However, there are no standardized methods for
performing online weight syncing. Open source projects
like SkyRL, VeRL, and TRL need to include their
own implementations of the weight syncing
infrastructure, leading to added complexity
for developers seeking to adopt vLLM as their
inference server for post-training workloads.
https://github.com/vllm-project/vllm/issues/31848

How much Workers are enough? I guess it depends
on I/O parallelism, CPU Memory parallelism, CPU
Processing parallelism, and now also

GPU Memory parallelism and GPU Processing
parallelism, and last but least you might have
a couple DMAs sitting here and there,

or even invoking a sort of RDMA. Quite amazing!

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]

#671873 — What are Flits and Phits? [Network on a Chip] (Re: GPU Elasticity: Collective Communications Libraries)

Hi,

Recently there was a paper somebody mentioning
a flit doing a ACK or NACK, to express
backpressure inside a Network on a Chip.

But what is a flit? It seems multiple
flits can be used to create the message
passing in one directiob before the

ACK or NACK in the other direction?

"The growing need for performance from
computing systems drove the industry into
the multi-core and many-core arena. In this
setup, the execution of a kernel (a program)
is split across multiple processors and the
computation happens in parallel

Flits represent logical units of information,
while phits represent the physical domain,
that is, phits represent the number of bits
that can be transferred in parallel in a
single cycle. Consider the Cray T3D. It has
an interconnection network which uses

flit level message flow control wherein each
flit is composed of eight 16-bit phits. That
means its flit size is 128bits and phit size
is 16bits. Also consider the IBM SP2 switch.
It also uses the flit level message flow
control, but its flit size is equal to its
phit size, which is set to 8 bits."
https://en.wikipedia.org/wiki/Flit_(computer_networking)#Example

Well my idea how this is realized in silicon
is rather foggy, I mean even the Hack project
from Nand 2 Tetris, does not show some gate level
schemes for flits and phits.

Could be an interesting extension. But somehow
the image of flits and phits inspired my channel
objects here below. But I am afraid they are fire
and forget, no ACK and NACK:

π-WAM Contest: 1 Million Packets with Prolog
https://medium.com/2989/ec3e91551773

Its amazing that a max_size(1) buffer
can beat an unbounded buffer!

LoL

Bye

Mild Shock schrieb:
> Hi,
> 
> How it started, NVIDIA being cool:
> 
> NCCL provides routines such as all-gather,
> all-reduce, broadcast, reduce, reduce-scatter,
> and point-to-point send and receive. These
> routines are optimized to achieve high
> bandwidth and low latency over PCIe,
> NVIDIA NVLink™, and other high-speed
> interconnects within a node and over
> NVIDIA networking across nodes.
> https://developer.nvidia.com/nccl
> 
> How its going, vLLM trying to be cool:
> 
> [RFC]: Native Weight Syncing APIs
> However, there are no standardized methods for
> performing online weight syncing. Open source projects
> like SkyRL, VeRL, and TRL need to include their
> own implementations of the weight syncing
> infrastructure, leading to added complexity
> for developers seeking to adopt vLLM as their
> inference server for post-training workloads.
> https://github.com/vllm-project/vllm/issues/31848
> 
> How much Workers are enough? I guess it depends
> on I/O parallelism, CPU Memory parallelism, CPU
> Processing parallelism, and now also
> 
> GPU Memory parallelism and GPU Processing
> parallelism, and last but least you might have
> a couple DMAs sitting here and there,
> 
> or even invoking a sort of RDMA. Quite amazing!
> 
> 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]

#671969 — The Mac Neo is a Budget Monster [GPU Channels] (Was: What are Flits and Phits? [Network on a Chip])

Hi,

Now I implemented some multiple producer
and multiple consumer channel objects for
WebGPU. The only API to integrate it user

facing into pi-WAM is this single predicate:

/**
  * flit(C):
  * The predicate succeeds in C with a new channel. The channel
  * can be used from within GPU backed π-WAM logical threads.
  */

The Mac Neo is a Budget Monster. While the
Ryzen AI Laptop cost around 1300.- CHF.
The Mac Neo was around 600.- CHF with all

extras. Here some performance results,
checking out whether channel objects scale,
when increasing their number to

communicate the same 1 millon packets:

Java performance:

AI Laptop	Single	Double
Ryzen	705.1	337.4
Neo	669.4	239.9

WebGPU performance:

AI Laptop	Single	Double
Ryzen	731.8	392.9
Neo	932.8	483.5

Cool! Java is also pretty cool, their
semaphore library is top notch. I couldn't
replicate the resulst with JavaScript yet,

seems their Atomics.wait() resp. Atomics.waitAsync()
is totally broken, using futex is mutex for
fools somehow. I also found some gremlins

attacking one of the GPUs. The Intel AI Laptop
fails the above experiment. Maybe its a driver
Vulkan versus OpenCL or something problem,

or the Lunar lake architecture is nonsense.

Bye

Mild Shock schrieb:
> Hi,
> 
> Recently there was a paper somebody mentioning
> a flit doing a ACK or NACK, to express
> backpressure inside a Network on a Chip.
> 
> But what is a flit? It seems multiple
> flits can be used to create the message
> passing in one directiob before the
> 
> ACK or NACK in the other direction?
> 
> "The growing need for performance from
> computing systems drove the industry into
> the multi-core and many-core arena. In this
> setup, the execution of a kernel (a program)
> is split across multiple processors and the
> computation happens in parallel
> 
> Flits represent logical units of information,
> while phits represent the physical domain,
> that is, phits represent the number of bits
> that can be transferred in parallel in a
> single cycle. Consider the Cray T3D. It has
> an interconnection network which uses
> 
> flit level message flow control wherein each
> flit is composed of eight 16-bit phits. That
> means its flit size is 128bits and phit size
> is 16bits. Also consider the IBM SP2 switch.
> It also uses the flit level message flow
> control, but its flit size is equal to its
> phit size, which is set to 8 bits."
> https://en.wikipedia.org/wiki/Flit_(computer_networking)#Example
> 
> Well my idea how this is realized in silicon
> is rather foggy, I mean even the Hack project
> from Nand 2 Tetris, does not show some gate level
> schemes for flits and phits.
> 
> Could be an interesting extension. But somehow
> the image of flits and phits inspired my channel
> objects here below. But I am afraid they are fire
> and forget, no ACK and NACK:
> 
> π-WAM Contest: 1 Million Packets with Prolog
> https://medium.com/2989/ec3e91551773
> 
> Its amazing that a max_size(1) buffer
> can beat an unbounded buffer!
> 
> LoL
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> How it started, NVIDIA being cool:
>>
>> NCCL provides routines such as all-gather,
>> all-reduce, broadcast, reduce, reduce-scatter,
>> and point-to-point send and receive. These
>> routines are optimized to achieve high
>> bandwidth and low latency over PCIe,
>> NVIDIA NVLink™, and other high-speed
>> interconnects within a node and over
>> NVIDIA networking across nodes.
>> https://developer.nvidia.com/nccl
>>
>> How its going, vLLM trying to be cool:
>>
>> [RFC]: Native Weight Syncing APIs
>> However, there are no standardized methods for
>> performing online weight syncing. Open source projects
>> like SkyRL, VeRL, and TRL need to include their
>> own implementations of the weight syncing
>> infrastructure, leading to added complexity
>> for developers seeking to adopt vLLM as their
>> inference server for post-training workloads.
>> https://github.com/vllm-project/vllm/issues/31848
>>
>> How much Workers are enough? I guess it depends
>> on I/O parallelism, CPU Memory parallelism, CPU
>> Processing parallelism, and now also
>>
>> GPU Memory parallelism and GPU Processing
>> parallelism, and last but least you might have
>> a couple DMAs sitting here and there,
>>
>> or even invoking a sort of RDMA. Quite amazing!
>>
>> 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]

#671972 — The luminaries of duct-tape engineering [Sweeney and Torvald] (Re: The Mac Neo is a Budget Monster [GPU Channels])

Hi,

We didn't find yet a library for our Think that
would support webgpu on the ARM architecture,
so its back to the browser flag and testing there.

The node.js package comes only with:

dist
+-- d3dcompiler_47.dll
+-- darwin-universal.dawn.node
+-- linux-arm64.dawn.node
+-- linux-x64.dawn.node
+-- win32-x64.dawn.node

Its a similar situation like with SVN. In some
communities its not common to provide a ARM build.
They rather use x86 till the end of the universe.

Although we think initiatives like the x86 Ecosystem
Advisory Group could be a clever marketing trick to
hide a funeral service. Adding "luminaries" such as

Tim Sweeney and Linus Torvald to the panel, is even
more so a joke, given that intel produces mutex bottlenecks
instead of futex, where f stands for fast, in their GPU

infrastructure. So who is the teacher and who are
the students? But why even try to create a collation
against ARM, it doesn't make any sense.

Bye

Mild Shock schrieb:
> Hi,
> 
> Now I implemented some multiple producer
> and multiple consumer channel objects for
> WebGPU. The only API to integrate it user
> 
> facing into pi-WAM is this single predicate:
> 
> /**
>   * flit(C):
>   * The predicate succeeds in C with a new channel. The channel
>   * can be used from within GPU backed π-WAM logical threads.
>   */
> 
> The Mac Neo is a Budget Monster. While the
> Ryzen AI Laptop cost around 1300.- CHF.
> The Mac Neo was around 600.- CHF with all
> 
> extras. Here some performance results,
> checking out whether channel objects scale,
> when increasing their number to
> 
> communicate the same 1 millon packets:
> 
> Java performance:
> 
> AI Laptop    Single    Double
> Ryzen    705.1    337.4
> Neo    669.4    239.9
> 
> WebGPU performance:
> 
> AI Laptop    Single    Double
> Ryzen    731.8    392.9
> Neo    932.8    483.5
> 
> Cool! Java is also pretty cool, their
> semaphore library is top notch. I couldn't
> replicate the resulst with JavaScript yet,
> 
> seems their Atomics.wait() resp. Atomics.waitAsync()
> is totally broken, using futex is mutex for
> fools somehow. I also found some gremlins
> 
> attacking one of the GPUs. The Intel AI Laptop
> fails the above experiment. Maybe its a driver
> Vulkan versus OpenCL or something problem,
> 
> or the Lunar lake architecture is nonsense.
> 
> Bye
> 
> Mild Shock schrieb:
>> Hi,
>>
>> Recently there was a paper somebody mentioning
>> a flit doing a ACK or NACK, to express
>> backpressure inside a Network on a Chip.
>>
>> But what is a flit? It seems multiple
>> flits can be used to create the message
>> passing in one directiob before the
>>
>> ACK or NACK in the other direction?
>>
>> "The growing need for performance from
>> computing systems drove the industry into
>> the multi-core and many-core arena. In this
>> setup, the execution of a kernel (a program)
>> is split across multiple processors and the
>> computation happens in parallel
>>
>> Flits represent logical units of information,
>> while phits represent the physical domain,
>> that is, phits represent the number of bits
>> that can be transferred in parallel in a
>> single cycle. Consider the Cray T3D. It has
>> an interconnection network which uses
>>
>> flit level message flow control wherein each
>> flit is composed of eight 16-bit phits. That
>> means its flit size is 128bits and phit size
>> is 16bits. Also consider the IBM SP2 switch.
>> It also uses the flit level message flow
>> control, but its flit size is equal to its
>> phit size, which is set to 8 bits."
>> https://en.wikipedia.org/wiki/Flit_(computer_networking)#Example
>>
>> Well my idea how this is realized in silicon
>> is rather foggy, I mean even the Hack project
>> from Nand 2 Tetris, does not show some gate level
>> schemes for flits and phits.
>>
>> Could be an interesting extension. But somehow
>> the image of flits and phits inspired my channel
>> objects here below. But I am afraid they are fire
>> and forget, no ACK and NACK:
>>
>> π-WAM Contest: 1 Million Packets with Prolog
>> https://medium.com/2989/ec3e91551773
>>
>> Its amazing that a max_size(1) buffer
>> can beat an unbounded buffer!
>>
>> LoL
>>
>> Bye
>>
>> Mild Shock schrieb:
>>> Hi,
>>>
>>> How it started, NVIDIA being cool:
>>>
>>> NCCL provides routines such as all-gather,
>>> all-reduce, broadcast, reduce, reduce-scatter,
>>> and point-to-point send and receive. These
>>> routines are optimized to achieve high
>>> bandwidth and low latency over PCIe,
>>> NVIDIA NVLink™, and other high-speed
>>> interconnects within a node and over
>>> NVIDIA networking across nodes.
>>> https://developer.nvidia.com/nccl
>>>
>>> How its going, vLLM trying to be cool:
>>>
>>> [RFC]: Native Weight Syncing APIs
>>> However, there are no standardized methods for
>>> performing online weight syncing. Open source projects
>>> like SkyRL, VeRL, and TRL need to include their
>>> own implementations of the weight syncing
>>> infrastructure, leading to added complexity
>>> for developers seeking to adopt vLLM as their
>>> inference server for post-training workloads.
>>> https://github.com/vllm-project/vllm/issues/31848
>>>
>>> How much Workers are enough? I guess it depends
>>> on I/O parallelism, CPU Memory parallelism, CPU
>>> Processing parallelism, and now also
>>>
>>> GPU Memory parallelism and GPU Processing
>>> parallelism, and last but least you might have
>>> a couple DMAs sitting here and there,
>>>
>>> or even invoking a sort of RDMA. Quite amazing!
>>>
>>> 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]

#671975 — Re: The Mac Neo is a Budget Monster [GPU Channels] (Was: What are Flits and Phits? [Network on a Chip])

Mild Shock wrote:

> facing into pi-WAM is this single predicate:
> 
> /**
>   * flit(C):
>   * The predicate succeeds in C with a new channel. The channel * can be
>   used from within GPU backed π-WAM logical threads. */
> 
> The Mac Neo is a Budget Monster. While the Ryzen AI Laptop cost around
> 1300.- CHF.
> The Mac Neo was around 600.- CHF with all

nothing

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

#671924 — Cristallina: Thank you for the Beam (Re: The Wuhan Virus that destroyed Python [ggml Manifesto])

Hi,

How it started:

Filming a vitamin B12 photoreceptor in action
https://www.psi.ch/de/news/science-features/filming-a-vitamin-b12-photoreceptor-in-action

How its going:

Elon Musk's potential FEL route could challenge EUV lithography
https://www.kucoin.com/news/flash/elon-musk-s-potential-fel-route-could-challenge-euv-lithography

Who will win the Nano Atom mover race,

will the USA OutChip its competitor China
and its supplier Asia in the next years?

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] | [standalone]

Page 7 of 7 — ← Prev page 1 2 3 4 5 6 [7]

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

csiph-web