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
- [Bugfix] Reject non-object structured_outputs with HTTP 400
- [Bugfix] Don't double-count local prefix cache stats on scheduling retries
- [Performance] Optimize multimodal embedding merger with static shape pattern for XLA and CUDA Graphs
- [Bugfix] Fix illegal memory access from a forward during a partial wake_up
- [Metrics][Spec Decoding] Add per-request acceptance rate Prometheus histogram
- [Bugfix][Core] Fix host memory leak from undrained new_block_ids
- [Bugfix] Fix FP8 MoE double memory allocation for non-gated models
- [Doc] Clarify profiling and benchmarking methodology
- [Model Runner V2] Support thinking_token_budget for mrv2
- [V1][Mamba] Cast copy metadata pointers to int64
- Docs
- Python not yet supported