Skip to content
ONNX Runtime DirectML Builds

QMoE CPU Performance Update (Up to 4x on 4-bit) #10483

Sign in to view logs

QMoE CPU Performance Update (Up to 4x on 4-bit)

QMoE CPU Performance Update (Up to 4x on 4-bit) #10483

Triggered via pull request February 17, 2026 03:12
@tianleiwutianleiwu
opened #27364
tlwu/20260216/qmoe_cpu_q4_perf
Status Success
Total duration 1h 50m 20s
Artifacts –

windows_dml.yml

on: pull_request
Windows GPU DML CI Pipeline
1h 29m
Windows GPU DML CI Pipeline
Fit to window
Zoom out
Zoom in

Annotations

6 warnings
Windows GPU DML CI Pipeline: onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1234
epilog offset from end of function exceeds 4095
Windows GPU DML CI Pipeline: onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1227
epilog offset from end of function exceeds 4095
Windows GPU DML CI Pipeline: onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1220
epilog offset from end of function exceeds 4095
Windows GPU DML CI Pipeline: onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1213
epilog offset from end of function exceeds 4095
Windows GPU DML CI Pipeline: onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1206
epilog offset from end of function exceeds 4095
Windows GPU DML CI Pipeline: onnxruntime/core/mlas/lib/amd64/QgemmU8X8KernelAvx2.asm#L1199
epilog offset from end of function exceeds 4095