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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Switch Rust regex engine for response parsing
- [Bugfix][Frontend] Accept typed tool choice and tool models in ChatCompletionRequest
- [CI] Enroll Language Models (Extended Generation) in automatic sharding; spawn in test_gemma's dummy-loader test
- [Bugfix][Frontend] Reject translation on models that cannot translate
- [ROCm] Add AITER CK DASH attention for Unlimited-OCR-2
- [Feature][Model] Add NCP-OLMo support for pure HF checkpoints
- [Build] Rewrite CUDA arch selection per target and preserve plain arch coverage
- [Bugfix][Quantization] Handle dict-valued Quark `algo_config` in `maybe_update_config`
- [Perf][DSA] Keep ShardQ projections sequence-sharded under SP
- [MM] Nemotron VL: resize images and video frames on the GPU with CV-CUDA
- Docs
- Python not yet supported