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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- fix(lora): _load_lora_config retry uses deterministic backoff without jitter — thundering herd risk
- [Bug]: lmcache_connector.start_load_kv asserts on degraded LMCache instead of honoring "recompute" fallback
- [Bugfix] Detect driver-level CUDA init before fork
- [XPU] Fix flash-attn k/v descale shape for compressed-tensors quantization
- [Bugfix] Restore logging disable level on exception in suppress_logging
- [Model] Initialize GDN dt_bias and A_log params as float32
- [Breakable Graph] add eager break for unified attention
- [RFC]: Model customized KVCache Planning
- Relax CuPy constraint to only exclude 14.1.0
- [Frontend] Split ServingRender into renderer and entrypoint.
- Docs
- Python not yet supported