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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: /v1/unload_lora_adapter never removes the adapter from the engine
- [Bugfix] mistral: malformed tool-call output should not become a 500
- [Bugfix][Frontend] Malformed `$defs` in a tool schema should be a 400, not a 500
- [Bug]: `MooncakeStoreScheduler` fatal assert "Missing current block table for store request" when a KV load failure recovery (#19330) reschedules the request
- [Kernel] Tune Qwen4Exp Triton MoE on H200
- [Bug]: padded KV page reshape uses a spec-page stride against a kernel-block size, so as_strided over-requests storage by the split ratio
- [Feature] Add SingProbe token-level probes for Ling 3.0
- [ROCm][MLA][DCP] Pad the AITER MLA decode head count to a native tile
- [Bugfix][Spec Decode] Isolate ngram_gpu compile cache
- [Bug]: Request-level tools render ahead of the system prompt in DeepSeek-V3.
- Docs
- Python not yet supported