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 supported41 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)
- [Bugfix][Core] Filter reasoning boundary tokens before structured-output FSM advance
- [Performance]Improve use_cascade_attention mechanism
- [Frontend] Report reasoning_tokens usage for chat completions; fix count for prompt-injected <think>
- [MRV2][Refactor] Migrate speculator feature flags into model code
- [Installation]: libcudart.so.13 required when torch-backend=cu129 on vllm v0.22.0
- fix(tracing): dual-emit legacy and current OTel GenAI token attributes
- [Bugfix] enable per-engine stats logging when api_server_count > 1
- [Core] Implement fine-grained timing spans for requests.
- Fix FlashInfer attention auto-selection on SM75 GPUs
- Docs
- Python not yet supported