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 supported62 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Fix/multibackend preferred block size
- [Security] Validate NIXL peer topology before rank expansion
- [Perf][Core][Mamba] Export prefill checkpoints at or before the initial-state column
- [ROCm] MonoKernel for GLM 5.2
- [Bugfix] Dequantize DeepSeek-V4 wo_a for non-DeepGEMM linear backends
- [Bugfix][Attention] Use a block size only when every backend prefers it
- [Bug]: token_indices_to_sample underflows past the request's query start with PP > 1 spec decode
- [Bugfix] Pin long-lived host buffers at their exact size
- [Refactor] Move model-specific env vars into vllm/models/<model>/envs.py
- Lightning perf pr
- Docs
- Python not yet supported