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
- [Warmup] Cover DSv4 sparse top-k and DFlash input-prep Triton specializations that JIT at first request
- [Security] Forward cache_salt into LMCache V1 keys
- [RFC]: Pluggable KV connector metrics on the Rust frontend via connector metrics descriptor
- [Metrics][Frontend] Pluggable KV connector metrics on the Rust frontend via connector metrics descriptor
- [Bug]: EngineCore worker crashes with "RuntimeError: cancelled" on first /v1/embeddings request (CPU, bge-m3)
- [Feature][KV Connector] Add UMBPStoreConnector for embedded and standalone DRAM
- [Bug]: New watermarking feature (v0.30.0) allows per-request opt-out even when server enforces --watermark-config
- [KV Offload] Request-free CPU->GPU prefetch primitive
- [Frontend] Add watermark_config.enforce to prevent per-request watermark opt-out
- [Test] Cover cumulative parallel sampling outputs
- Docs
- Python not yet supported