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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ci] Move 3 entrypoints tests to h200_35gb queue
- [Feature]: Add separate_reasoning option for OpenAI chat completion API
- [Usage]: GLM-5/GLM-5.1 deployment on L40 with vLLM
- [Bug]: Not support role tool of image
- [Cleanup]Simplify UnitaryKVCacheCoordinator hash_block_size assert
- [Bug]: Port collision ([Errno 98] Address already in use) when launching multiple LLM(tensor_parallel_size=2) instances concurrently on a single node (V1 Engine)
- [Feature]: GRPC interface for Pooling
- [Bug]: Possible to get GPU OOM for DP/EP
- [Bug] Fix fused_qk_norm_rope 32-bit QKV offset overflow
- Revert "[Bugfix] mamba: run single-token extends as decodes (#42430)"
- Docs
- Python not yet supported