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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [New Model]: facebook/multi-token-prediction
- [build][misc] remove nvidia runtime docker base image
- [Bug]: When cuda_graph is enabled, RunTimeError:NCCL error is reported using nvidia-nccl-cu11
- [Bug]: `flash_attn_cuda.varlen_fwd` may output a bad result when enabling prefix caching
- [Bug]: Illegal memory access
- [Feature]: Access to user information in scheduler
- feat: adds user information to the input of the scheduler
- [Bugfix] [Core] don't schedule prefill if freeing kv cache
- Cohere model output speed about 5 tokens per second on vllm.
- [Bug]: error when requesting max-num-seqs with speculation
- Docs
- Python not yet supported