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
- PP on docker: gloo control plane resolves to bridge IP (535ms per send) and presents as a long-context decode collapse β suggest defaulting GLOO_SOCKET_IFNAME=lo for same-netns ranks
- [Attention] Support FlashInfer re-paging for packed BLHNC KV caches
- Restrict v1 engine zmq IPC sockets to a per-user private directory
- [Bug]: SMG MoRI-IO PD disagg
- WIP] Fix ExampleHiddenStatesConnector for Hybrid KV Cache Manager
- [Misc] Use multithreading to accelerate server memcpy.
- [Bugfix] Package the SM90 DeepGEMM mHC register lifetime fix
- [Metrics] Redesign engine sleep-state telemetry for partial sleep/wake
- [Bugfix][Parser] Constrain tool-call markers by token ID in engine stβ¦
- [ROCm][Perf][Attention] Reduce temporary allocations in sparse-indexer prefill
- Docs
- Python not yet supported