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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: [v0.22]MooncakeStoreConnector causes incorrect KV cache memory pre-check calculation for DeepSeek models(PP2 TP8) (fallback to MHA dimension)
- [Bug]: --enable-prompt-tokens-details omits zero cached tokens
- [Misc] Add unit test for chunk_local_cumsum kernels
- [Bugfix][Core] Filter reasoning boundary tokens before structured-output FSM advance
- [Bug]: `wake_up(tags=["weights"])` + forward → illegal memory access (KV cache still asleep)
- [Performance]Improve use_cascade_attention mechanism
- [Frontend] Report reasoning_tokens usage for chat completions; fix count for prompt-injected <think>
- [Bugfix] Two-phase KV allocation for cross-group prefix cache hits (supersedes #33775)
- [BugFix] Fix Traceback due to malformed MessagePack (#24655)
- [MRV2][Refactor] Migrate speculator feature flags into model code
- Docs
- Python not yet supported