// Official vendor repos

vLLM 项目

8 tracked official repos · 39 releases in the last 30 days.

01Latest releases

vllm-project/vllm-metal v0.32.0.dev20261022015004 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0.dev20261021162405 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0.dev20261021111544 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0.dev20261021103316 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0.dev20261021101232 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0.dev20261021025750 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0.dev20261021020515 Patchpre

Community maintained hardware plugin for vLLM on Apple Silicon
vllm-project/vllm-metal v0.32.0 Patch

Community maintained hardware plugin for vLLM on Apple Silicon

Repo	Category	★	Latest	Licence
vllmA high-throughput and memory-efficient inference and serving engine for LLMs	Inference & local runtime	94.9k	v0.32.02026-10-18	Apache-2.0
vllm-omniA framework for efficient model inference with omni-modality models	Speech & audio	7,293	v0.32.0rc12026-10-20	Apache-2.0
semantic-routerAn open, programmable decision layer for models and compute.	Model gateways & routers	6,243	v0.4.02026-09-27	Apache-2.0
aibrixCost-efficient and pluggable Infrastructure components for GenAI inference	Inference & local runtime	5,157	v0.8.02026-10-13	Apache-2.0
llm-compressorState-of-the-art LLM compression, built for production inference with vLLM	Inference & local runtime	3,897	0.9.0.52026-10-10	Apache-2.0
vllm-ascendCommunity maintained hardware plugin for vLLM on Huawei Ascend	Inference & local runtime	2,996	v0.30.0rc12026-10-14	Apache-2.0
production-stackvLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization	Inference & local runtime	2,682	vllm-stack-0.1.132026-09-30	Apache-2.0
vllm-metalCommunity maintained hardware plugin for vLLM on Apple Silicon	Inference & local runtime	1,898	v0.32.0.dev202610220150042026-10-22	Apache-2.0