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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Installation]: libcudart.so.13 required when torch-backend=cu129 on vllm v0.22.0
- [Spec Decode] Adaptive K*: Dynamic speculation length from per-position acceptance rates
- [Tests] Gate Step3VL under Transformers v5
- fix(tracing): dual-emit legacy and current OTel GenAI token attributes
- [Bugfix] enable per-engine stats logging when api_server_count > 1
- [Bugfix] Don't crash EngineCore when structured output grammar compilation fails
- [Core] Implement fine-grained timing spans for requests.
- Fix FlashInfer attention auto-selection on SM75 GPUs
- fix: default-disable FlashInfer sampler on consumer Blackwell GPUs (SM120/SM121)
- [Bugfix][V1] Don't resume scheduler on a partial wake_up (illegal memory access, #44395)
- Docs
- Python not yet supported