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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [CI] Remove unused docker/Dockerfile.nightly_torch
- [Bug]: FlashInfer warmup crash on Blackwell NVFP4: non_blocking=None passed to Tensor.to()
- [Docs] Clarify structured outputs configuration for Qwen3 reasoning mode
- [Bugfix] [DP] Fix create too many placement groups
- [Bug]: vLLM 0.13.0, GLM4.6, H20; encountered error: torch.AcceleratorError: CUDA error: an illegal memory access was encountered
- [Bug]: EPLB hangs in several cases
- [Performance]: Testing vLLM upgrade results in significant TTFT degradation
- [V1][Core] Rename engine_core to engine_core_client for clarity
- [Bug]: The final streaming response chunk is missing the finish_reason.
- [BugFix][P/D] set correct media_type for streaming responses in PD separation proxy
- Docs
- Python not yet supported