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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Benchmarks] Add --disable-connection-pooling flag to vllm bench serve
- [Bugfix][Frontend] Disable /v1/chat/completions for base models without chat templates
- [Security] Add Host header validation and improve security guide
- fix: compensate chunk split offset in Whisper segment timestamps (closes #32588)
- [Bug]: VLLM tries to load "inductor" instead of custom compiler
- [Bug]: DeepSeek 3.2 P/D Disaggregation Support
- [Bug]: Triton CompilationError in speculative decoding (draft_model)
- [Bug]: V1 engine workers die after idle period (SystemError: PyCFunction / EngineDeadError) — TP=2, multiprocessing
- RTX 5090 (SM120): NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 fails to start, No NvFp4 MoE backend supports the deployment configuration
- Bump actions/stale from 10.1.1 to 10.2.0
- Docs
- Python not yet supported