onnxruntime icon indicating copy to clipboard operation
onnxruntime copied to clipboard

Published 20 hours ago • verified publisher icon microsoft

[JS/WebGPU] GroupQueryAttention rewrite

Open satyajandhyala opened this issue 8 months ago • 1 comments

Description

Implement JSEP GroupQueryAttention

Motivation and Context

Required to enable certain LLM models to run using WebGPU.

satyajandhyala avatar Jun 06 '24 02:06 satyajandhyala