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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Introduce PaddingConfig to combine GPU cudagraph_capture_sizes and TPU num_tokens_paddings
- [Frontend] Plugin for OpenAI server (prototype)
- [P/D][Feature] Support using NIXL together with PP
- [Build] No need to use the more restrictive gencode then necessary
- [RFC][UX]: debug mode for vLLM-compile
- [Bug]: vLLM crashes when using --enable-sleep-mode with Blackwell PRO 6000 GPUs
- [RFC]: Support KV Cache sparse with common framework
- [Feature]: serve gpt-oss BF16 weights
- [Bug]: Voxtral-Small-24B-2507 Does Not Support Pipeline-Parallel
- [Bug]: Devstral-Small-2507 tool parsing issue when streaming
- Docs
- Python not yet supported