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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [1/2][MRV2] Remove the dependency of MRV2 DBO from MRV1
- [Bug]: Qwen GDN models fail to start with CPU weight offloading without UVA
- [Bugfix] Move offloaded A_log and dt_bias to the GPU in the Qwen GDN warmup
- [Bugfix][UMBP] Reject DRAM watermarks that keep MORI from evicting
- [Bugfix][KV Offload][P2P] Fail a dead peer's sibling ports on the same host at once (opt-in)
- [Security] Bound decoded image copies before preprocessing
- [Security] Bound Ovis2.5 processed media allocations
- [Rust Frontend] gRPC Render service with streaming Derender; multimodal, LoRA, logprobs and stop strings for render
- [CI] Run Anthropic contract tests on CPU
- [Bug]: `npcache` silently serves stale weights after the source `.bin` checkpoint changes
- Docs
- Python not yet supported