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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Parser] Namespace Cohere tool grammar rules by position
- [ROCm][CI] Run the nightly Python 3.14 smoke test on AMD
- [Core] Add collective_rpc_per_engine to return every data-parallel engine's worker results
- [Perf][Frontend] Trim per-chunk and per-request work in the completions stream
- [Bugfix][Rust Frontend] Bump fastokens to 0.3.6
- [Feature][Quantization] Rewrite compressed-tensors regex targets on load
- [RFC]: Word-level timestamps for speech models from per-request encoder outputs
- [Bug]: granite_20b_fc chat template fails to render any conversation with a system message
- [Bugfix][Rust Frontend] Accept auxiliary frames in the mock engine
- [Online quantization] Add requantize_from to select re-quantized checkpoint layers based on dtype
- Docs
- Python not yet supported