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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: "ValueError: No tokenizer file found in directory" when serving Qwen3-Omni
- [Bugfix] Fix empty response under concurrent requests
- [Bug]: LoRA loading fails with Fused MoE when data parallelism (DP > 1) is enabled
- [Bugfix][Tool Parser] Fix crash when parameter description contains parentheses
- [MoE Refactor] Only use RouterMethodType for flashinfer
- [CI] Split responses API MCP tests into separate CI step
- [Feature][AMD][ROCm] Refactor VLLM_ROCM_USE_AITER env vars to config
- [Bugfix] Upgrade Numba to fix segfault on CUDA drivers version 580
- [Hybrid] Simplify mamba block size logic for `all` mode
- [WIP] PCP simplification
- Docs
- Python not yet supported