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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Docs] Reorganize examples docs.
- [Bug]: Report "System message must be at the beginning." When using qwen3.6-27B
- [Bugfix] Fix missing format argument in tensor IPC stale tensor warning
- [Feature]: unsupported architecture
- [Bugfix] Changed speech to text chunk timestamp to cumlative approach
- [EPLB] Add offline mapping support
- [Bugfix][Qwen3-Next] Force a/b contiguity in fix_query_key_value_ordering
- [Feature]: Support DeepSeek V4 flash on SM120 with Triton fallback
- [Bug]: Triton MLA decode kernel shape mismatch for Mistral-Small on ROCm when TP > 1
- [ROCm][Kernel] Add HybridW4A16LinearKernel: Triton prefill + HIP skinny decode
- Docs
- Python not yet supported