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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature] Add completed_at field to ResponsesAPI
- fix(scheduler): discard async tokens on all V1 preemption paths
- [WIP] [ROCm] [Doc] Update ROCm attention selection doc and test coverage
- [Specialized Models] Implement optimized DeepSeek V3.2 NVFP4
- [Bugfix] Opt-in INFO prompt summaries for request logging (--enable-log-request-prompts)
- [Doc]: improve disaggregated prefilling guide
- [Bug]: Streaming last chunk contains non-empty tool_calls with empty fields "type" causing type validation error
- [RFC]: Add Mooncake Store Connector for Shared KV Cache Reuse
- [Bug]: There should be flag/setting to collect environment
- [Bug]: NemotronH Super 120B crashes mid-decode when two vLLM instances run concurrently on AGX Thor unified memory
- Docs
- Python not yet supported