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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend][Anthropic] Honor thinking.type=disabled in Messages API
- [Feature]: [ROCm][Hy4] Add calibrated FP8 KV-cache support for sparse MLA
- [Bugfix][Frontend] Avoid IndexError when verbose ASR emits only EOS
- [Bugfix][Frontend] Preserve whole messages in Responses auto truncation
- docs: document NIXL KV connector metrics aggregation semantics
- [RFC]: Publish Mooncake Store residency once per complete block
- [Kimi-K3][Perf] Dispatch GEMM for vision patch embedder
- [Feature][Multimodal] Add opt-in CPU preprocessing process workers
- [Frontend] Remove the slow tokenizer mode
- [Bugfix][Frontend] Respect tokenizer padding side in renderer
- Docs
- Python not yet supported