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 supported4 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Doc]: Performance/Optimization Page doesn't mention Pipeline Parallel Size
- [Bug]: Failed to generate normal outputs on deepseek-vl2-tiny's MoE LM backbone
- [Usage]: Capability gap between open-source models and GPT-4o
- [Bug]: server crash when glm4-9b-chat got an image request
- [Bug]: structured output bug (or just support less) using xgrammar
- [Bug]: Profiling on vLLM server hangs when --num-scheduler-steps > 1
- [Misc]: For disaggregated prefill with multiple decode instances, drop_select might not enough
- Dummy PR
- Type-fix: make execute_model output type optional
- [FEATURE] Enables /score endpoint for embedding models
- Docs
- Python not yet supported