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
- add model test1
- [WIP][Benchmarking] Benchmarking script for v1 attention backends
- [Misc] Add LMCache async save support
- [Kernel] Add EP support for cutlass_moe_fp4
- [Feature]: try to gracefully destroy process group in `vllm serve` on handling Ctrl+C (prior to processes termination)
- [ROCm] Upgrade aiter version
- [Core] Support sleep mode for cuda graph
- [Feature]: Flashinfer per-request
- [Misc] Harden `SamplingParams.from_optional` support
- [Not Ready][VLM] Deprecate original format Phi-4-MM model
- Docs
- Python not yet supported