Popular repositories Loading
-
qwen36-k100ai-w8a8-optimization
qwen36-k100ai-w8a8-optimization PublicReproducible single-GPU Qwen3.6-35B-A3B W8A8 inference tuning for Hygon K100AI (gfx928) on vLLM 0.18.1.
Python 1
-
minimax-h3-k100ai-optimization
minimax-h3-k100ai-optimization PublicMiniMax H3 INT8 ConvRot optimization and dual-K100AI QKV/Attention inference for Hygon K100AI (gfx928)
Python
-
qwen36-27b-k100ai-w8a8-optimization
qwen36-27b-k100ai-w8a8-optimization PublicQwen3.6-27B W8A8 single-GPU inference optimization for Hygon K100AI/gfx928, with no-MTP and MTP reproducible paths.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.