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 supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: offline inference with ray fails on multinode
- [Performance]: How to Improve Performance Under Concurrency
- [Bug]: vllm.LLM does not seem to re-initialize for distributed inference with subsequent models with Offline Inference
- [Bug]: Bfloat16 or Half are not compatible with HF float16/bfloat16 result.
- [Bug]: Incoherent Offline Inference Single Video with Qwen2-VL
- [Usage]: Are prompts processed sequentially?
- [Bug]: "gettid" was not declared error when build from source for cpu with version after v0.6.1
- [Bugfix] Generate multiple different prompts in benchmark_prefix_caching.py based on --num-prompts
- [Bug]: "Using Tesla V100 to load the GPTQ-Int4 model results in all output being exclamation marks."
- [Feature]: support for Cambricon MLU
- Docs
- Python not yet supported