mxfp6

Here are 2 public repositories matching this topic...

High-performance runtime extensions for vLLM.

performance optimize vllm llm-inference sm120 qwen3-5 qwen3-8 exl3 mxfp6

Blackwell-optimized llama.cpp bundle with DFlash2, MXFP6/MXFP8/NVFP4, TurboQuant KV, and GPU-resident speculative handoff.

blackwell llama-cpp speculative-decoding mxfp8 turboquant dflash2 mxfp6

To associate your repository with the mxfp6 topic, visit your repo's landing page and select "manage topics."