vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: There is any performance benchmark between running vLLM server via docker image and python?
- [wip] fuse rope fp8 through mla_rope_quantize_fp8
- [Feature][P1]: Investigate and Implement Zstd Compression for Docker Images
- [Quantization] Use torch.from_numpy to avoid deep copy when iterate GGUF weights
- [Feature]: GGUF model with architecture qwen3vlmoe is not supported yet.
- [Bug]: [H200] DeepSeek-R1 EP 1.5x TTFT due to MoE backend behavior changes
- [Feature]: More control over expert parallelism (--moe_ep_size, --moe_tp_size)
- [Bug]: Qwen3-32B use eagle3 crash
- [Feature]: Batch invariant: Enable TRITON_MLA with prefix-caching
- [Bug]: sagemaker_sessions on a shared cluster
- Docs
- Python not yet supported