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
- [Feature]: Request for Ascend NPU support
- [Kernel] Fix identical branches
- [Feature]: FlashAttention 3 support
- [BigFix] Fix the lm_head in gpt_bigcode in lora mode
- [Bug]: vllm.engine.async_llm_engine.AsyncEngineDeadError: Background loop has errored already.
- [Usage]: How to run a custom post_init() function after loading the transformers model using LLM class
- [Feature]: control over llm_engine placement when multiple gpus are available.
- [Bug]: RuntimeError: aclose(): asynchronous generator is already running
- [Feature]: Hybrid Attention
- [Bug]: VLLM's output is unstable version==0.5.1
- Docs
- Python not yet supported