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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [DO NOT REVIEW] Add rms_norm_per_block_quant UE8M0 handling for B200
- fix(rocm): remove workaround causing invalid argument on Qwen3.5 with TP=2
- [Bug] MultiConnector bypasses the deprecated-signature shim and breaks old-style child connectors
- [ModelRunner V2] Speculative Decoding NGram GPU Implementations
- Enable TurboQuant for GPT-OSS
- Revert "[NVFP4] NVFP4 MOE emulation fallback for H100/MI300/MI350, standardize `TritonExperts` usage for OCP MX emulation" (#35737)
- [Bugfix] Fix Triton MLA decode when Lk > Lv (split c_kv / k_pe cache)
- [RFC][vLLM IR]: Batch Invariance Dispatching in vLLM IR
- [ROCm][DSv3.2] Adopt new paged-MQA-logits API + cached logits buffer with defensive padding
- [Bugfix][Distributed] Tear down stale NCCL group on reinit in NCCLWeightTransferEngine
- Docs
- Python not yet supported