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 supported15 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [gpt-oss] Add model_identity to system message retrieval for harmony chat template
- [Bug]: H200 GPT-OSS-120B has perf drop
- fix(gguf): Auto-select compatible dtype for GGUF models on Blackwell
- [RFC]: Token Padding Strategy for FP8 GEMM Performance Optimization
- Optimize workspace memory in DeepGEMM.
- [KVConnector] Auto-downgrade to PIECEWISE cudagraph mode for layerwise async ops
- [Bug]: MM cache AssertionError crashes engine, causes request aborts
- [Attention] Full CG support for llama4 and remove use of deprecated properties
- Add GPU memory usage warning system
- Specify the kv_cache dtype of the draft model
- Docs
- Python not yet supported