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
- [Bug]: Block-scaled FP8 (compressed-tensors W8A8) crashes on load on SM120 Blackwell (RTX PRO 6000), v0.24.0 — DeepGEMM "Unknown SF transformation" assertion
- [Bugfix][CPU] Fix data-parallel EngineCore processes all binding to the same NUMA node
- [Bug]: fp8 KV cache + prefix caching truncates generation (ignore_eos bypassed) on Qwen3.5-NVFP4
- [Attention Backend] Select split-K per shape in HPC Attention Decode Backend, add integration tests
- [Rust Frontend]: Added olmo3 reasoning parser
- fix(security): bound MRoPE temporal positions to prevent engine crash
- [Bug]: Deploying the GLM5.2-nvfp4 model using the 0.24.0 image , the model occasionally outputs "!!!!!!!!!!!!!!!!!" in the thinking phase,
- [ZenCPU] Changes with respect to relevant cpu tests for ZenDNN
- Fix Responses API null field serialization
- Recover GLM-4.7 tool calls missing arg_key start
- Docs
- Python not yet supported