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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Responses API Harmony output parser raises `ValueError: Unknown channel: comment` at response assembly and closes the /v1/responses SSE stream before `response.completed`
- [Bugfix][Frontend] Drop Harmony messages on unrecognized channels in Responses output parsing instead of raising
- [ROCm][AITER][CI] Test MoE sorting-backend dispatch env-var matrix
- [Tracing] Parent llm_request span to the active FastAPI span
- [CI] Raise Spec Decode N-Gram + Suffix timeout 20m -> 30m
- [FS-Offloading] Batching for FS threadpool
- [Security] Keep copied tool closers inside Qwen parameter values
- [Frontend] Let the HF config override Harmony detection
- [Bugfix][XPU] Reset oneCCL's collective chain after XPU graph capture
- a16w16 gemm for router gate on k3 (WIP)
- Docs
- Python not yet supported