#vllm

AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash

Python

89

health

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

vllm-project/semantic-router

Go

87

health

A programmable Mixture-of-Models router for heterogeneous LLM inference

vllm-project/vllm-ascend

Python

85

health

Community maintained hardware plugin for vLLM on Huawei Ascend