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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Security] Disable cookie persistence on shared media HTTP clients
- [CI/Build] Use FileStore for DeepEP test rendezvous
- [Test] Retry transient GSM8K dataset downloads
- [Bugfix] Don't assert the GPU lacks native FP4 in the Marlin fallback warning
- [Bugfix][Quantization] Fix online MoE weight conversion `KeyError: 'weight_scale'` with Humming
- [bugfix][kernel] honor leading strides in sm100 standard and blockwise fp8 gemm
- [Profiler] Synchronize iteration windows across DP ranks
- Optimize atomic MiniMax M3 marker lookup
- [Bugfix][Frontend] Keep inline system messages in place for encoder-based tokenizers (Anthropic API)
- [Bugfix] FlashInfer `flashinfer_b12x` MoE backend runs W4A16 checkpoints as W4A4
- Docs
- Python not yet supported