vllm-project/vllm-metal

[RFC] Redundant KV-cache reads during speculative-decode verification 2 days ago

help wanted

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

[Feature]: Support P/D disaggregation via RDMA over thunderbolt about 1 month ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

vLLM Metal Model Support 2 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

vllm-metal performance vs vllm-swift 2 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

Qwen 3.6 27B model not working 3 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

Server stalls mid-stream for large context requests, never sends [DONE] or closes connection 4 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

[Feature] Support for Mamba-style Linear Attention Layers in Models 6 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

Enhancement: Distributed Inference with RAY + vLLM-Metal on Apple Silicon 6 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

Support for MoE Models (Qwen-MoE, etc.) & Mamba Cache on Apple Silicon 6 months ago

good first issue

vllm-project/vllm-metal

1.4K

Community maintained hardware plugin for vLLM on Apple Silicon

Python

Open Issues Need Help