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
- [Performance]: W4Afp8 is slower than FP8-W8A8
- [Installation]: vllm 0.15.1 pip install still rely on torch2.9.1
- [Bug]: `maybe_serialize_tool_calls()` fails to verify the `tool_calls` type
- [Performance]: Refactor the exponential_ method calling to improve performance of TopKTopPSampler
- [Feature]: Qwen3 realtime asr
- [ROCm] [CI] Add new fusion test cases that are relevant to vLLM IR Ops
- [EPLB] Add communication config autotuning
- [Usage]: Option to set system_fingerprint?
- [Bug]: Online FP8 quantization does not split MoE expert weights across GPUs with TP/EP for Qwen3NextForCausalLM
- [Bug]:
- Docs
- Python not yet supported