Add it to a GitHub README or profile β the card updates as the ranking changes:
ROCm-compatible fork of Bittensor β Full PyTorch 2.4 ROCm support β Wallet, Metagraph, Dendrite fully working.
AMD/NVIDIA GPU cluster infrastructure β ~300 GPU deployment, ROCm, kernel tuning, multi-node benchmarking
FLUX.1-dev on AMD Radeon consumer GPUs β fast, low-VRAM, and shippable. Backport patches + benchmarks for torchao + diffusers group_offload on ROCm.
Production-grade local LLM deployment stack β llama.cpp, Ollama, GGUF/GGML, ROCm AMD, 14B to 80B models
Production infrastructure scripts β ROCm setup, multi-GPU config, server hardening, LLM deployment automation
Multi-GPU tensor/context parallel diffusion on AMD ROCm β with the patch that makes it actually work.