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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: torch.compile startup time logging not correct
- [Doc]: Multi-node distributed guide issues
- [Bug]: potential inconsistencies in shared memory due to lack of memory ordering guarantees
- [RFC]: Internal Process-level Fault Tolerance for vLLM
- [Bug]: Segfault in NCCL cuMemCreate during distributed engine initialization on 3080
- [Feature]: AFD support load customer connect model from local path.
- [Usage]: How to install nightly version??? Why this command doesn't work?
- [Bug]: vLLM 0.10.2/0.11.0 bench serve deadlocks when benchmarking DeepSeek-R1-BF16 (sglang 0.4.7), with processes hanging indefinitely during script execution
- [CI/Build] Skip spec decode tests using Triton backend
- [Bug]: AsyncTP pass doesn't work on B200
- Docs
- Python not yet supported