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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [MoE] Use sorted fused-MoE path on integrated GPUs for multi-token batches (#63943)
- [Metrics] Add vllm:kv_admission_refusals counter
- [Recipe] Qwen3.5: keep configuration-specific content out of the guides
- [Bugfix][DSA] Split FlashInfer sparse MLA calls above the 65535 gridDim.z limit
- [Bugfix][CPU] Resolve the process cgroup when reading the memory limit
- [ROCm][CI] Re-enable VLLM_GPU_SYNC_CHECK=error in the ROCm test image
- [Feature] Support per-model Hugging Face and ModelScope sources
- [Bugfix] FlashInfer flashinfer_b12x MoE backend runs W4A16 checkpoints as W4A4
- [Bugfix][Spec Decode] Propagate dictionary hf-overrides to speculative draft models
- [Metrics] Add vllm:kv_load_failed_tokens counter
- Docs
- Python not yet supported