Skip to content

Enable graph capture for WebGPU models and DML continuous decoding tests#2099

Draft
qjia7 wants to merge 1 commit intomainfrom
enable-graph-capture-webgpu-ci
Draft

Enable graph capture for WebGPU models and DML continuous decoding tests#2099
qjia7 wants to merge 1 commit intomainfrom
enable-graph-capture-webgpu-ci

Conversation

@qjia7
Copy link
Copy Markdown
Contributor

@qjia7 qjia7 commented Apr 24, 2026

  • Add enable_graph_capture flag to model download config in _test_utils.py
  • When enable_graph_capture=True and device=webgpu, pass enable_webgpu_graph=true to the model builder so generated models have enableGraphCapture=1
  • Enable graph capture for qwen-2.5-0.5b model (used by guidance tests)
  • Remove #if !USE_DML guard from multi-turn guidance tests since PR [WebGPU] Support continuous decoding (RewindTo) with graph capture #2083 fixed RewindTo for DML (DML always uses graph capture/static mask)

- Add enable_graph_capture flag to model download config in _test_utils.py
- When enable_graph_capture=True and device=webgpu, pass enable_webgpu_graph=true
  to the model builder so generated models have enableGraphCapture=1
- Enable graph capture for qwen-2.5-0.5b model (used by guidance tests)
- Remove #if !USE_DML guard from multi-turn guidance tests since PR #2083
  fixed RewindTo for DML (DML always uses graph capture/static mask)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant