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
- [Usage]: RuntimeError: CUDA error: invalid device ordinal
- [Feature]: Support setting tool-call-parser to auto
- [Usage]: AssertionError: collective_rpc should not be called on follower node
- [Bug]: Gemma-3 multimodal models (4b/12b/27b) fail with torch.compile assertion error
- [Feature]: Support `include_reasoning` request parameter for non-harmony models
- [Feature]: Implement `get_kv_cache_stride_order` for all classes
- [Usage]: how to serve quantized Qwen3-Reranker-8B
- [CPU][PPC64] Fix bf16 path in mla_decode.cpp
- Pass modality information in embed_multimodal
- [Bug]: GLM47 Tool Call Bug
- Docs
- Python not yet supported