Hackernews posts about MI400

  1. AMD Helios MI400 System Architecture at Hot Chips 2026 (www.servethehome.com)
    10 points by pella 27 days ago | 2 comments
  2. AMD MI400 GPU at Hot Chips 2026 (www.servethehome.com)
    3 points by pella 27 days ago | discuss
  3. Cross-vendor byte-identical inference for a 72B LLM (AMD MI300X vs. Nvidia H100) (zenodo.org)
    9 points by ashsyngh 26 days ago | discuss
  4. A Deep Dive into LDS Optimizations on AMD Instinct MI450 GPUs (rocm.blogs.amd.com)
    3 points by ks6g10 23 days ago | discuss
  5. A Deep Dive into LDS Optimizations on AMD Instinct MI450 GPUs (rocm.blogs.amd.com)
    2 points by matt_d 20 days ago | discuss
  6. CES 2026: Taking the Lids Off AMD's Venice and MI400 SoCs (chipsandcheese.com)
    136 points by rbanffy 9 months ago | 82 comments
  7. AMD Says "Helios" Racks and MI400 Series GPUs on Track for 2H 2026 (www.nextplatform.com)
    4 points by rbanffy 7 months ago | discuss
  8. HPE Launches AMD EPYC Venice Instinct MI400 and Nvidia Vera Rubin Compute Blades (www.servethehome.com)
    3 points by PaulHoule 10 months ago | discuss
  9. AMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 – SemiAnalysis (semianalysis.com)
    2 points by rbanffy over 1 year ago | discuss
  10. AMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 – SemiAnalysis (semianalysis.com)
    2 points by rbanffy over 1 year ago | discuss
  11. AMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 (semianalysis.com)
    2 points by pella over 1 year ago | discuss
  12. HPE Launches New AMD EPYC Venice Instinct MI400 and Vera Rubin Compute Blades (www.servethehome.com)
    1 points by rbanffy 10 months ago | discuss
  13. DeepSeek V4 Flash on a Single AMD MI300X (github.com)
    382 points by zhoutong about 2 months ago | 109 comments
  14. The AMD Radeon Instinct MI300A's Giant Memory Subsystem (chipsandcheese.com)
    212 points by pella over 1 year ago | 99 comments
  15. Bringing Up DeepSeek-V4-Flash on AMD MI300X (fergusfinn.com)
    120 points by kkm 4 months ago | 25 comments
  16. Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guide (rocm.blogs.amd.com)
    71 points by matt_d about 2 months ago | 11 comments
  17. Exploring inference memory saturation effect: H100 vs. MI300x (dstack.ai)
    57 points by latchkey almost 2 years ago | 12 comments
  18. Boosting Computational Fluid Dynamics Performance with AMD MI300X (rocm.blogs.amd.com)
    47 points by latchkey over 1 year ago | 45 comments
  19. Why isn't AMD's MI300X competitive? (newsletter.semianalysis.com)
    46 points by colonCapitalDee 5 months ago | 36 comments
  20. An EPYC Exclusive for Azure: AMD's MI300C – By George Cozma (chipsandcheese.com)
    41 points by rbanffy almost 2 years ago | 14 comments
  21. Nvidia wants 10Gbps HBM4 to blunt AMD's MI450, report claims (www.tomshardware.com)
    21 points by rbanffy 12 months ago | discuss
  22. Attention is NOT all you need: Qwerky-72B trained using only 8 AMD MI300X GPUs (substack.recursal.ai)
    20 points by jtatarchuk over 1 year ago | 3 comments
  23. Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs (dstack.ai)
    11 points by latchkey almost 2 years ago | 3 comments
  24. Using AMD MI300X for High-Throughput, Low-Cost LLM Inference (www.herdora.com)
    8 points by technoabsurdist about 1 year ago | discuss
  25. AMD 2.0 – New Sense of Urgency, MI450X Chance to Beat Nvidia, Nvidia's New Moat (semianalysis.com)
    7 points by elorant over 1 year ago | discuss
  26. $15 Linksys LN1303 (MX400) Battletest from Woot – New Life Thanks to FOSS (nixsanctuary.com)
    7 points by paulcarroty almost 2 years ago | discuss
  27. AMD Hints at Big FP64 Increases in MI430X GPU as Ozaki Underwhelms (www.hpcwire.com)
    5 points by rbanffy 6 months ago | discuss
  28. MI300X vs. H100 vs. H200 Benchmark Part 1: Training (newsletter.semianalysis.com)
    5 points by nl 10 months ago | discuss
  29. AMD 2.0 – New Sense of Urgency| MI450X Chance to Beat Nvidia| Nvidia's New Moat (semianalysis.com)
    5 points by pella over 1 year ago | discuss
  30. Inter-APU Communication on AMD MI300A Systems via Infinity Fabric: A Deep Dive (arxiv.org)
    4 points by matt_d about 1 year ago | discuss
  31. DeepSeek R1 inference performance: MI300X vs. H200 (dstack.ai)
    4 points by latchkey over 1 year ago | discuss
  32. Sizing Up MI300A's GPU (chipsandcheese.com)
    4 points by klelatti over 1 year ago | discuss
  33. Microsoft beat H200 Deepseek inference with MI300 (techcommunity.microsoft.com)
    3 points by galeos over 1 year ago | 1 comments
  34. A Fast Attention Kernel for MI300X, Written in Hip, Not Assembly (moonmath.ai)
    3 points by latchkey 3 months ago | discuss
  35. Repomind – 256K context coding agent on a single AMD MI300X (FP8) (github.com)
    3 points by sardor_r1 5 months ago | discuss