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
- [Bug]: glm4-9b-chat-lora-merge model with VLLM for concurrent requests, the process gets stuck and returns an "Aborted request" error.
- [Bug]: preifx cache reuse
- [Bug]: pipepline parallel performance issue for 1 sample.
- [Feature]: support for Cambricon MLU
- [Performance]: Low GPU utilization - is it normal?
- [RFC]: Add support for IBM Spyre accelerator
- [Feature]: support SageAttention
- [Usage]: Llama-3.1-70B-Instruct best arguments for throughput at scale for multiple users
- [Bug]: Llama-3.2-11B-Vision gives OOM error on 96GB H100
- [Usage]: Multimodal content with benchmark_serving.py
- Docs
- Python not yet supported