Hackernews posts about MI300

1. 01
   

   newDeepSeek V4 Flash on a Single AMD MI300Xgithub.com

   ▲ 382zhoutong62d💬 109savesaved
2. 02
   

   newThe AMD Radeon Instinct MI300A's Giant Memory Subsystemchipsandcheese.com

   ▲ 212pella625d💬 99savesaved
3. 03
   

   newBringing Up DeepSeek-V4-Flash on AMD MI300Xfergusfinn.com

   ▲ 120kkm124d💬 25savesaved
4. 04
   

   newExploring inference memory saturation effect: H100 vs. MI300xdstack.ai

   ▲ 57latchkey668d💬 12savesaved
5. 05
   

   newBoosting Computational Fluid Dynamics Performance with AMD MI300Xrocm.blogs.amd.com

   ▲ 47latchkey627d💬 45savesaved
6. 06
   

   newWhy isn't AMD's MI300X competitive?newsletter.semianalysis.com

   ▲ 46colonCapitalDee160d💬 36savesaved
7. 07
   

   newAn EPYC Exclusive for Azure: AMD's MI300C – By George Cozmachipsandcheese.com

   ▲ 41rbanffy671d💬 14savesaved
8. 08
   

   newAttention is NOT all you need: Qwerky-72B trained using only 8 AMD MI300X GPUssubstack.recursal.ai

   ▲ 20jtatarchuk551d💬 3savesaved
9. 09
   

   newBenchmarking Llama 3.1 405B on 8x AMD MI300X GPUsdstack.ai

   ▲ 11latchkey725d💬 3savesaved
10. 10
    

    newCross-vendor byte-identical inference for a 72B LLM (AMD MI300X vs. Nvidia H100)zenodo.org

    ▲ 9ashsyngh40ddiscusssavesaved
11. 11
    

    newUsing AMD MI300X for High-Throughput, Low-Cost LLM Inferencewww.herdora.com

    ▲ 8technoabsurdist449ddiscusssavesaved
12. 12
    

    newMI300X vs. H100 vs. H200 Benchmark Part 1: Trainingnewsletter.semianalysis.com

    ▲ 5nl302ddiscusssavesaved
13. 13
    

    newInter-APU Communication on AMD MI300A Systems via Infinity Fabric: A Deep Divearxiv.org

    ▲ 4matt_d409ddiscusssavesaved
14. 14
    

    newDeepSeek R1 inference performance: MI300X vs. H200dstack.ai

    ▲ 4latchkey565ddiscusssavesaved
15. 15
    

    newSizing Up MI300A's GPUchipsandcheese.com

    ▲ 4klelatti622ddiscusssavesaved
16. 16
    

    newMicrosoft beat H200 Deepseek inference with MI300techcommunity.microsoft.com

    ▲ 3galeos528d💬 1savesaved
17. 17
    

    newA Fast Attention Kernel for MI300X, Written in Hip, Not Assemblymoonmath.ai

    ▲ 3latchkey105ddiscusssavesaved
18. 18
    

    newRepomind – 256K context coding agent on a single AMD MI300X (FP8)github.com

    ▲ 3sardor_r1150ddiscusssavesaved
19. 19
    

    newMy First Multi-GPU Kernel: Writing All-to-All for AMD MI300Xgau-nernst.github.io

    ▲ 3mfiguiere336ddiscusssavesaved
20. 20
    

    newDissecting CPU-GPU Unified Physical Memory on AMD MI300A APUsarxiv.org

    ▲ 3matt_d411ddiscusssavesaved
21. 21
    

    newThe Microsoft Azure HBv5 and AMD MI300Cwww.servethehome.com

    ▲ 3ashvardanian683ddiscusssavesaved
22. 22
    

    newGigabyte G383-R80-AAP1 AMD Instinct MI300A Server Review – ServeTheHomewww.servethehome.com

    ▲ 2rbanffy491d💬 1savesaved
23. 23
    

    newReal world(ish) DeepSeek V4 Flash performance on a single MI300Xmatthusby.github.io

    ▲ 2mhusby45ddiscusssavesaved
24. 24
    

    newCreating custom kernels for the AMD MI300huggingface.co

    ▲ 2skidrow365ddiscusssavesaved
25. 25
    

    newCreating custom kernels for the AMD MI300huggingface.co

    ▲ 2skidrow368ddiscusssavesaved
26. 26
    

    newCreating custom kernels for the AMD MI300huggingface.co

    ▲ 2skidrow369ddiscusssavesaved
27. 27
    

    newCreating custom kernels for the AMD MI300huggingface.co

    ▲ 2skidrow436ddiscusssavesaved
28. 28
    

    newShow HN: Chisel – Profile AMD MI300X kernels locallygithub.com

    ▲ 2technoabsurdist469ddiscusssavesaved
29. 29
    

    newBenchmarking MI300X Memcpyscalarlm.ghost.io

    ▲ 2latchkey522ddiscusssavesaved
30. 30
    

    newMi300 Huggingfacehuggingface.co

    ▲ 2galeos537ddiscusssavesaved

· edit