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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Rust Frontend] Support --override-generation-config
- [Perf][KV Connector] Remove superseded prompt-end Mamba checkpoints
- [Quark] Rotate MXFP4 MoE activations before both GEMMs
- [HiSparse] Alternative to #55398: land P/D imports in resident pages through a generic transfer view
- [Bugfix][DSv4.1] Use int64 row offsets in the K-cache gather kernels
- [Bugfix] Prune broken chunk_scaled_dot_kkt autotune configs on Hopper
- [Bugfix][CPU] Validate hash-MoE tid2eid expert ids at the op boundary
- [Bugfix][Frontend] Pool HF fast tokenizers in BaseRenderer so concurrent truncation stays per request
- [Bugfix][Structured Output] Retry a failed cached xgrammar compile without the cache
- [Bug]: [InferHunt] olmo3 tool parser silently drops HTML-like plain text in streaming responses
- Docs
- Python not yet supported