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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Ignore DeepSeek V4 thinking sampling overrides
- [CI] Retry transient tokenizer loads in detokenizer tests
- [Bugfix] Reserve max-num-queued-reqs slots at preflight so a burst is rejected before render
- [Bug]: V1 thinking budget corrupts a multi-token reasoning_end_str under speculative decoding
- [Bug]: MiniMax M2 tool parser drops </think> with minimax_m2_append_think
- [XPU] Enable host registration for shared KV offload
- [Bugfix] Keep closing </think> delimiter in MiniMax M2 append-think mode
- run glm5next dense on cpu
- [Attention][Perf] Use natural-log LSE views for FlashInfer DCP prefill
- [Bugfix] Keep Hunyuan A13B streaming envelope open until </answer> closes
- Docs
- Python not yet supported