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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Doc] Refactor import statements for `oneshot` in quantization docs to support newer llm-compressor version
- [Bugfix] Actually enable serialize_messages for harmony Responses (related to #26185)
- [Bug]: [Spec Decode] ngram speculation performance regression at higher concurrany
- [benchmark] Support generalized SSE protocol
- [Bug]: `guided_choice` and `guided_decoding_backend` don't work when `enable_thinking=False` for Qwen3
- [Usage]: How to set the expert id on each EP by myself after setting EP in Deepseek (how to reorder experts?)
- [Bug]: torch._dynamo.exc.FailOnRecompileLimitHit: recompile_limit reached with fullgraph=True on 2x RTX2080Ti
- [RFC]: Consolidated tool call parser implementations by type (JSON, Python, XML, Harmony)
- [test/dnm] do not merge: ci-infra dummy PR
- [UX] Include NVTX in cuda.txt
- Docs
- Python not yet supported