Hackernews posts about MI350

  1. Kimi K3 Running on AMD MI350X with SGLang (twitter.com)
    4 points by ronfriedhaber 25 days ago | discuss
  2. DeepSeek V4 Flash on a Single AMD MI300X (github.com)
    382 points by zhoutong 17 days ago | 109 comments
  3. Running Kimi K3 on MI355X at Better Performance per Dollar Than B300 (www.wafer.ai)
    220 points by ilreb 19 days ago | 113 comments
  4. Attention Decode on AMD MI450 GPUs: A Gluon Kernel Optimization Guide (rocm.blogs.amd.com)
    71 points by matt_d 24 days ago | 11 comments
  5. Day 0 Kimi-K3 Inference Deployment with Atom on AMD Instinct MI355X GPUs (www.amd.com)
    9 points by stevefan1999 24 days ago | discuss
  6. AMD and Anthropic Announce Partnership to Deploy Up to 2 Gigawatts of MI450 GPUs (ir.amd.com)
    2 points by roboror 30 days ago | discuss
  7. AMD's Freshly-Baked MI350: An Interview with the Chief Architect (chipsandcheese.com)
    128 points by pella about 1 year ago | 75 comments
  8. ROCm 7.0 Goes Into Preview With MI350X/MI355X Support, Performance Improvements (www.phoronix.com)
    5 points by AbuAssar about 1 year ago | discuss
  9. AMD announces MI350X and MI355X AI GPUs (www.tomshardware.com)
    3 points by rbanffy about 1 year ago | 1 comments
  10. AMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 – SemiAnalysis (semianalysis.com)
    2 points by rbanffy about 1 year ago | discuss
  11. AMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 – SemiAnalysis (semianalysis.com)
    2 points by rbanffy about 1 year ago | discuss
  12. AMD Advancing AI: MI350X and MI400 UALoE72, MI500 UAL256 (semianalysis.com)
    2 points by pella about 1 year ago | discuss
  13. From MI350 to MI500: AMD's Bold AI Accelerator Roadmap Through 2027 (www.storagereview.com)
    2 points by rbanffy about 1 year ago | discuss
  14. AMD Instinct MI350 Launch Event Coverage (www.servethehome.com)
    2 points by rbanffy about 1 year ago | discuss
  15. AMD MI350 and CDNA 4 Architecture Launched with ROCm 7 (www.servethehome.com)
    2 points by rbanffy about 1 year ago | discuss
  16. AMD Data Center GPUs Explained: MI250X, MI300X, MI350X and Beyond (www.bentoml.com)
    1 points by djhu9 12 months ago | discuss
  17. The AMD Instinct MI350 – ServeTheHome (www.servethehome.com)
    1 points by rbanffy about 1 year ago | discuss
  18. The AMD Radeon Instinct MI300A's Giant Memory Subsystem (chipsandcheese.com)
    212 points by pella over 1 year ago | 99 comments
  19. Bringing Up DeepSeek-V4-Flash on AMD MI300X (fergusfinn.com)
    120 points by kkm 3 months ago | 25 comments
  20. Exploring inference memory saturation effect: H100 vs. MI300x (dstack.ai)
    57 points by latchkey over 1 year ago | 12 comments
  21. Occupancy Math on the AMD MI355X: A From-First-Principles Guide (indianspeedster.github.io)
    50 points by skidrow 2 months ago | 8 comments
  22. Boosting Computational Fluid Dynamics Performance with AMD MI300X (rocm.blogs.amd.com)
    47 points by latchkey over 1 year ago | 45 comments
  23. Why isn't AMD's MI300X competitive? (newsletter.semianalysis.com)
    46 points by colonCapitalDee 4 months ago | 36 comments
  24. An EPYC Exclusive for Azure: AMD's MI300C – By George Cozma (chipsandcheese.com)
    41 points by rbanffy over 1 year ago | 14 comments
  25. AMD Instinct MI325X to Feature 256GB HBM3E Memory, CDNA4-Based MI355X with 288GB (videocardz.com)
    40 points by kristianp almost 2 years ago | 18 comments
  26. Nvidia wants 10Gbps HBM4 to blunt AMD's MI450, report claims (www.tomshardware.com)
    21 points by rbanffy 11 months ago | discuss
  27. 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
  28. Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs (dstack.ai)
    11 points by latchkey almost 2 years ago | 3 comments
  29. Using AMD MI300X for High-Throughput, Low-Cost LLM Inference (www.herdora.com)
    8 points by technoabsurdist about 1 year ago | discuss
  30. 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
  31. State-of-the-Art Performance on AMD MI355 – In 14 Days (www.modular.com)
    6 points by jedharris 10 months ago | discuss
  32. MI300X vs. H100 vs. H200 Benchmark Part 1: Training (newsletter.semianalysis.com)
    5 points by nl 9 months ago | discuss
  33. 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
  34. Inter-APU Communication on AMD MI300A Systems via Infinity Fabric: A Deep Dive (arxiv.org)
    4 points by matt_d 12 months ago | discuss
  35. DeepSeek R1 inference performance: MI300X vs. H200 (dstack.ai)
    4 points by latchkey over 1 year ago | discuss
  36. Sizing Up MI300A's GPU (chipsandcheese.com)
    4 points by klelatti over 1 year ago | discuss