onnxruntime
[webgpu] Fix multihead-attention for ort-web-tests
#24485
Merged

[webgpu] Fix multihead-attention for ort-web-tests #24485

fs-eire merged 2 commits into microsoft:main from jchen10:mha
jchen10
jchen10
qjia7
qjia7 commented on 2025-04-21
guschmue guschmue added ep:WebGPU
guschmue
azure-pipelines
fs-eire
jchen10 [webgpu] Fix multihead-attention for ort-web-tests
e42e741e
jchen10 Compute total_sequence_length conditionally for GQA
aa0e089f
jchen10 jchen10 force pushed from e6df1c88 to aa0e089f 1 year ago
jchen10
fs-eire
azure-pipelines
fs-eire
fs-eire approved these changes on 2025-04-29
fs-eire fs-eire merged 45134763 into main 1 year ago
jchen10 jchen10 deleted the mha branch 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone