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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: FlashInfer autotuning crash with CUDA 13.0
- [Feature]: Fix all of the mypy check
- [Bug]: failed to build from source on sm120 machine
- [Feature]: Better base64 to torch tenser
- Add missing opentelemetry dependency to base docker image
- [Frontend][gpt-oss] Allow system message to overwrite model identity
- [FusedMoE] Remove cuda hard-code in dual stream execution
- [DOC] fix the rocm installation doc
- [Bug]: `vllm bench serve` incorrectly calculates ITL for openai-chat with reasoning, tool calling, or harmony models
- [ROCm][MHA] add dispatch logic for triton and aiter MHA
- Docs
- Python not yet supported