-
Notifications
You must be signed in to change notification settings - Fork 40
Pull requests: intel/torch-xpu-ops
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
layernorm: supplement for adaptive wg size adjustment
#1711
opened May 29, 2025 by
weishi-deng
Loading…
Add cases to skip list for test_transformers.py and remove passed cases
#1710
opened May 29, 2025 by
PenghuiCheng
Loading…
Optimize roi_align on BMG
hw: BMG
kernel_optimization
#1698
opened May 26, 2025 by
jianyizh
Loading…
Temp fix for bug in scale-out profiling by adding env variable to disable profiler around allreduce
#1697
opened May 23, 2025 by
frost-intel
•
Draft
run distributed test on xelink, and enable WA with FI_PROVIDER=tcp
#1694
opened May 23, 2025 by
daisyden
Loading…
Optimize work_group reduce for GroupNorm Forward
kernel_optimization
#1688
opened May 21, 2025 by
yucai-intel
Loading…
Enhanced Adaptive Average Pooling 2D Backward Kernel: Performance Improvements and Code Simplification
kernel_optimization
#1658
opened May 14, 2025 by
chunhuanMeng
Loading…
Add
check_op_perf
utility to summary op performance automatically
#1650
opened May 9, 2025 by
xytintel
Loading…
[Nightly] Add op performance regression check
#1622
opened Apr 28, 2025 by
RUIJIEZHONG66166
Loading…
Removed some cases from skip list for the issue disappeared
#1607
opened Apr 24, 2025 by
PenghuiCheng
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2025-05-26.