[cuda backend] reduce memory consumption on gemma4_31b by running embedding in int8 #1407
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Test WebGPU Backend | |
| on: | |
| schedule: | |
| - cron: 0 2 * * * | |
| push: | |
| branches: | |
| - main | |
| - release/* | |
| tags: | |
| - ciflow/nightly/* | |
| pull_request: | |
| workflow_dispatch: | |
| concurrency: | |
| group: ${{ github.workflow }}--${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }} | |
| cancel-in-progress: true | |
| jobs: | |
| test-webgpu: | |
| uses: ./.github/workflows/_test_backend.yml | |
| with: | |
| backend: webgpu | |
| flows: '["webgpu"]' | |
| ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }} | |
| timeout: 120 | |
| run-linux: true |