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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC] Weight Reload Correctness for RL
- [Bug]: Mistral v11 streaming parser merges parallel tool calls into one when content precedes [TOOL_CALLS] in a single delta
- [Bug]: Responses API: explicit "background": null or "truncation": null fails response construction (confusing 400 / broken SSE stream)
- [Bug]: Gibberish output with VLLM_XPU_ENABLE_XPU_GRAPH=1 on 2x Intel Arc Pro B70 Battlemage GPU
- [Bugfix] Skip Dynamic SD schedule for autoregressive speculator decode CUDA graphs
- [Bugfix] Dynamic video sampling should reject invalid video metadata before decoding
- [Bug]: echo=true kills the stream with a ValidationError when the last message content is a list (multimodal content format) — non-streaming succeeds
- [Bugfix] Disable FA3 AOT scheduling for spec-decode proposer
- [Bugfix][Spec Decode] Auto-enable async scheduling for draft models
- [Bug]: DeepSeek V3 streaming tool parser truncates final arguments not ending with '"}' when the end token shares the delta
- Docs
- Python not yet supported