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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: `/v1/completions/derender` drops requested `prompt_logprobs`
- [Bug]: `/v1/chat/completions/batch` leaks hidden reasoning through logprobs and token IDs when `include_reasoning=false`
- [Bug]: AssertionError in _update_from_kv_xfer_finished when LMCache KV load fails on heterogeneous attention models
- [Bug]: Spec decode hits illegal memory access when the draft model's context is shorter than the target's
- [RFC]: Add native AliceAI model support
- [Bug]: HunYuan Dense V1 fails CUDA graph capture on v0.29 — HF dynamic RoPE does a host-side sync during capture
- [KV Offload][FS] Opt-in per-block CRC32C checksums
- [Bug]: AMD mirror declarations disagree with test-amd.yaml steps - declared MI355/MI250 groups carry the MI300 agent pool and gfx942 lanes
- [Bugfix][API] Materialize tool_calls in TokenizeChatRequest to fix unpicklable ValidatorIterator (#57738)
- [Bug] [watermarking]: reference detection server does not support dual_key_gumbel; detector alpha default disagrees with generation default
- Docs
- Python not yet supported