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
- [KV Cache] Skip the zero fill in allocate_kv_cache when the platform does not need it
- [Startup UX]: Serial per-process Python imports across the API server → EngineCore → worker tree add significant startup time
- [Bugfix] Propagate SIGTERM during engine startup
- fix: prevent path traversal outside cache directory in FilesystemResolver (#59270)
- [HiSparse] Standardize terminology and add a nomenclature to the design doc
- [Performance]: FlashAttention backend rebuilds KV-cache views on every call (+~21 µs CPU/layer since #44455)
- [ROCm][Perf]: Tune FP8 Gemma4 MLP gate-up and down projs for prefills on gfx942
- [ROCm][AMD] Qwen3.8-Flash-Next gfx950 / MI355X Performance Optimization
- [Bugfix][Parser] Extract Granite tool names from the top-level object
- [Perf][Parser] Avoid incremental argument conversion in batch parsing
- Docs
- Python not yet supported