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
- [Perf] Rotate q/k as a packed zero-copy view in Qwen-VL vision attention
- [Bugfix][Kimi-K3] Fix usage.prompt_tokens over-counting generation prefix tokens
- [Bugfix] Fix RustToolParser streaming final flush
- [Model][Gemma4] Expose per-layer parameters
- [Bug]: use_heterogeneous_vocab (TLI) silently bypassed when use_local_argmax_reduction is enabled
- [ROCm] Migrate W4A16 FlyDSL MoE to AITER API
- [Bugfix][EPLB] Transport E8M0 expert state as byte views
- [Bug]: gemma4 parser keeps literal quote characters when the model writes array/object string values in plain JSON or Python syntax instead of <|"|>
- [ROCm][Perf] Skip redundant sparse index remap on non-indexer layers
- [Bugfix][Spec Decode] Replace path heuristics with checkpoint method inference
- Docs
- Python not yet supported