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]: MTP speculative decoding cannot start under pipeline parallelism — SupportsPP demanded of the draft model
- [Docs] extract_hidden_states supports chunked prefill
- [RFC]: vLLM Native Reusable Engine Snapshot Sleep (L3)
- Enhance engine snapshot management and API lifecycle
- fix(missing_documentation): Class `RequestOutputKind` in vllm/sampling_params.py has no
- [Core] Add shared-disk weight transfer backend
- [Bug]: VLLM_BATCH_INVARIANT does not cover convolution, used in VAE blocks
- [Bug]: DeepSeek-V4-Flash-0731 + DSpark fails to start on vLLM 0.27.0 / H100 sm90 (DeepGEMM CUDA_ERROR_ILLEGAL_ADDRESS); works on 0.26.0
- [Bugfix][V1] Chunk prompt-logprobs logits to bound the activation peak
- [Bugfix] Handle HarmonyError in process_chunk to fix gpt-oss streaming 500s
- Docs
- Python not yet supported