Skip to content

Support w8a8 fp8 block-wise quantization #3229

Support w8a8 fp8 block-wise quantization

Support w8a8 fp8 block-wise quantization #3229

Triggered via pull request December 25, 2024 16:01
Status Cancelled
Total duration 1m 13s
Artifacts

pr-test.yml

on: pull_request
Matrix: unit-test-backend-1-gpu
unit-test-frontend
51s
unit-test-frontend
unit-test-backend-2-gpu
50s
unit-test-backend-2-gpu
performance-test-1-gpu-part-1
1m 1s
performance-test-1-gpu-part-1
performance-test-1-gpu-part-2
45s
performance-test-1-gpu-part-2
performance-test-2-gpu
0s
performance-test-2-gpu
accuracy-test-1-gpu
46s
accuracy-test-1-gpu
accuracy-test-2-gpu
51s
accuracy-test-2-gpu
Fit to window
Zoom out
Zoom in

Annotations

20 errors
unit-test-backend-1-gpu (6-15)
The run was canceled by @github-actions[bot].
unit-test-backend-1-gpu (23-30)
The run was canceled by @github-actions[bot].
unit-test-backend-1-gpu (30-100)
The run was canceled by @github-actions[bot].
performance-test-2-gpu
The run was canceled by @github-actions[bot].
unit-test-backend-2-gpu
The run was canceled by @github-actions[bot].
unit-test-backend-2-gpu
The operation was canceled.
unit-test-backend-1-gpu (15-23)
The run was canceled by @github-actions[bot].
unit-test-backend-1-gpu (15-23)
The operation was canceled.
performance-test-1-gpu-part-2
The run was canceled by @github-actions[bot].
performance-test-1-gpu-part-2
The operation was canceled.
unit-test-frontend
The run was canceled by @github-actions[bot].
unit-test-frontend
The operation was canceled.
accuracy-test-1-gpu
The run was canceled by @github-actions[bot].
accuracy-test-1-gpu
The operation was canceled.
accuracy-test-2-gpu
The run was canceled by @github-actions[bot].
accuracy-test-2-gpu
The operation was canceled.
performance-test-1-gpu-part-1
The run was canceled by @github-actions[bot].
performance-test-1-gpu-part-1
The operation was canceled.
unit-test-backend-1-gpu (0-6)
The run was canceled by @github-actions[bot].
unit-test-backend-1-gpu (0-6)
The operation was canceled.