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 supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: speed regression 0.6.2 => 0.6.3?
- [Bug]: guided_grammer fails only on Mixtral models
- [Feature]: Consider parallel_tool_calls parameter at the API level
- [Bug]: Logprob values are affected by sampling parameters and are incompatible with OpenAI API
- [Usage]: Regarding VLLM Structured Output Doubts
- [Bug]: Error with structured output inference after upgrade 0.6.2->0.6.3
- [Bug]: RuntimeError: Error in model execution (input dumped to /tmp/err_execute_model_input_20241016-170451.pkl): view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
- [Bug]: Speculative decoding breaks guided decoding.
- [Bug]: When using the latest 0.6.3, No module named 'vllm._version' appears
- [Usage]: Obtaining success / error rate % metrics
- Docs
- Python not yet supported