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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Add Buffered Response Scheduling Policy
- [Bug]: Multiple dispatch failed for 'torch._ops.aten.permute.default' with Inductor freezing.
- [Bug]: Speculative decoding support for mamba models
- [Bug]: Repeated, wrong results of FP8-Dynamic Llava-OneVision regardless input images
- [Bug]: Harmony parser skips last tokens in speculative decoding in streaming responses
- [Usage]: How to disable reasoning for gpt-oss-120b
- [RFC]: SLA-Tiered Scheduling for Latency/Throughput Optimization
- [Bug]: The find_matches function took 15 seconds to process 175 images in a single request.
- [Installation]: download wheel by commit:not found
- [Usage]: Is it possible to configure P2P kv-cache in multi-machine and multi-gpu scenarios?
- Docs
- Python not yet supported