Hackernews posts about MI300
- 01AMD Instinct MI350P First Look: 144GB HBM3E in a 600W PCIe Cardwww.storagereview.com
- 02
- 03DeepSeek V4 Flash on a Single AMD MI300Xgithub.com
- 04The AMD Radeon Instinct MI300A's Giant Memory Subsystemchipsandcheese.com
- 05Bringing Up DeepSeek-V4-Flash on AMD MI300Xfergusfinn.com
- 06
- 07Boosting Computational Fluid Dynamics Performance with AMD MI300Xrocm.blogs.amd.com
- 08Why isn't AMD's MI300X competitive?newsletter.semianalysis.com
- 09An EPYC Exclusive for Azure: AMD's MI300C – By George Cozmachipsandcheese.com
- 10Attention is NOT all you need: Qwerky-72B trained using only 8 AMD MI300X GPUssubstack.recursal.ai
- 11
- 12
- 13MI300X vs. H100 vs. H200 Benchmark Part 1: Trainingnewsletter.semianalysis.com
- 14
- 15
- 16Sizing Up MI300A's GPUchipsandcheese.com
- 17Microsoft beat H200 Deepseek inference with MI300techcommunity.microsoft.com
- 18
- 19
- 20My First Multi-GPU Kernel: Writing All-to-All for AMD MI300Xgau-nernst.github.io
- 21
- 22Gigabyte G383-R80-AAP1 AMD Instinct MI300A Server Review – ServeTheHomewww.servethehome.com
- 23VibeSys Builds a Qwen3.5-397B Engine on MI300A, 2.3× Tuned SGLangsyfi.cs.washington.edu
- 24Real world(ish) DeepSeek V4 Flash performance on a single MI300Xmatthusby.github.io
- 25Creating custom kernels for the AMD MI300huggingface.co
- 26Creating custom kernels for the AMD MI300huggingface.co
- 27Creating custom kernels for the AMD MI300huggingface.co
- 28Creating custom kernels for the AMD MI300huggingface.co
- 29
- 30Benchmarking MI300X Memcpyscalarlm.ghost.io
- 31Mi300 Huggingfacehuggingface.co
- 32Supercharge DeepSeek-R1 Inference on AMD Instinct MI300Xrocm.blogs.amd.com
· edit