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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: System crash: Rust panic loading a tiktoken vocab file with duplicate ranks
- [Bug] fastsafetensors ParallelLoader broadcasts on group.WORLD; PP-scoped draft loads deadlock
- [Bugfix] Fix ZMQ port TOCTOU race in shm_broadcast MessageQueue
- [Frontend][Responses API] Support assistant message `phase`
- [Bugfix][MoE] Fall back to torch for unsupported expert counts in topk_softplus_sqrt
- [Bugfix][Tool Calling] Validate Qwen3 tool names in Parser Engine
- [Bug]: Qwen 3.* models go into doom loop if you use strict mode with tools without arguments.
- [Doc] Clarify Docker image tag availability
- [Rocm] Fix LMcache support issues for the kimik3-dspark model
- [RFC]: Add a fused MoE routing Backend for out-of-tree accelerators
- Docs
- Python not yet supported