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
- Validate request indices and sampler sizes before engine work
- Cap the cumulative length of realtime sessions
- [Rust Frontend] Support stop strings in the token generate route
- [Quantization][CT] fix the mxfp4 inference for MiniMax-M3 with CT format.
- [Bug] DeepSeek-V4-Flash-0731 intermittently emits malformed DSML tool-call start wrapper on v0.27.1 + DSpark
- [Bug][DSV4-Flash][DSpark] v0.27 weight loader regressed — KeyError routed_experts.w13_weight_scale (v0.26 gracefully skipped)
- [ROCm][DSv4] Add FlyDSL fused mega-MoE backend for DeepSeek V4
- [Perf] Move context_lens compute into prefill path for Minimax
- [XPU] [Linear] [MXFP8] enable torch as mxfp8 linear backend
- [CI/Build][torch.compile] Add E2E correctness test for QK-norm+RoPE fusion
- Docs
- Python not yet supported