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
- [RFC]: Add runtime weight update API
- [RFC]: proper resource cleanup for LLM class with file-like usage
- [Bug]:Qwen2-57B-A14B 两卡 推理报错
- [Bug]: `flash_attn_cuda.varlen_fwd` may output a bad result when enabling prefix caching
- [Bug]: Illegal memory access
- [Bugfix] [Core] don't schedule prefill if freeing kv cache
- [Installation]: vllm on NVIDIA jetson AGX orin
- [Feature]: Initial LLM token
- [RFC]: Implement disaggregated prefilling via KV cache transfer
- [Usage]: how to use marlin kernel for GPTQ model
- Docs
- Python not yet supported