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
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Tool Parser] Preserve raw control characters in Pythonic arguments
- [Bug][KV Connector] Load-failure report arriving after the owner was preempted: blocks stay cached, `fail` is not applied, stale output can be delivered
- [Feature] Chi-squared and perplexity watermarking
- [KV Offload] Check /dev/shm for every local DP engine; explain EFAULT
- [Perf] Fuse GLM-5.x MoE finalize into the next RMSNorm's all-reduce
- [Bugfix][KV Connector] Handle load failures after preemption
- [Bugfix][KV Connector] MoRIIO: treat FINISHED_STOPPED as producer decode completion
- [Feature][Whisper] Support srt and vtt response formats for speech-to-text APIs
- [Feature][Quantization] Add online Hadamard rotations before RMSNorm
- [Bugfix][NIXL] Keep push progress off model thread
- Docs
- Python not yet supported