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][Model Loader] Keep the weight lock file name within the 255-byte limit
- [Core][ROCm][Perf] Kimi-K3 enable prefill checkpoints on ROCm and fix prefix cache accounting
- [Bug]: thinking_token_budget: generation collapses into a repetition loop exactly at budget exhaustion
- [Bug]: Promoted partial prefix-cache entries reference a parent hash removed in the same batch
- [Bugfix] Re-anchor promoted partial prefix-cache entries on the surviving block-aligned ancestor
- [ROCm][Perf][Tracking Issue]: GLM-5.3-Flash
- [RFC] feat(scheduler): implement Shortest Remaining Prefill First (SRPF) policy with starvation aging
- [Bugfix][Quantization] Add Humming to the W4A8 (INT4xFP8) MoE oracle
- [Bugfix][Quantization] Give LM heads standard linear metadata
- [Bug]: EngineCore input socket thread dies on an undecodable request and the core stays alive but stops accepting requests
- Docs
- Python not yet supported