Popular repositories Loading

1. genesis-vllm-patches genesis-vllm-patches Public

   Production-grade runtime patches for vLLM (45+ patches) — Qwen3.6-35B-A3B-FP8 hybrid GDN+MoE on NVIDIA Ampere (SM 80-86). 127 tok/s MTP free-form, 99 tok/s suffix tool-call (max 175). TurboQuant k8…

   Python 29 1

2. vllm vllm Public

   Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python