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
- [Bug]:几个大的token超限制请求之后GPU KV cache usage持续升高一直接近100%,几个小时不下降,最后重启解决
- [Feature]: need args to pass set_process_title function
- [RFC]: Remove redundant multi-modal input preprocessing during disaggregated inference
- [Bug]: calculate_kv_scales=True isn't doing anything
- [Bug] GLM-4.5V fails to load weights with KeyError: 'blocks.0.attn.qkv.weight'
- [Performance]: non-optimal performance of `linear` for small batches
- [Tracking Issue]: Qwen3-next performance optimisations
- [Feature]: Heterogeneous TP per Pipeline Stage (uneven TP across PP)
- Support PP on tpu_inference
- [Bug]: api_server.py: error: unrecognized arguments: /root/models/Qwen3-8B
- Docs
- Python not yet supported