Umar Arshad

Use RUNTIME_DEPENDENCIES to collect dependencies of binaries Description ----------- * Use the RUNTIME_DEPENDENCIES feature to collect binaries to install dependencies Changes to Users ---------------- N/A Checklist --------- - [x] Rebased...

This PR adds a new memory manager example and fixes the native alloc function so that it ignores the af_memory_manager object. Description ----------- * Creates a new memory manager example...

gpu: intel: Optimize reusable layer normalization using work-group based reductions

1

# Description This pull request adds an alternative kernel that performs better under certain conditions compared to the sub-group reduction kernel previously implemented. The new kernel uses the work_group_reduce_add function...

Missing functions

6

- [x] arg (phase angle in radians) - [ ] epsilon - [ ] erfinv - [ ] erfcinv - [x] factorial - [x] trunc - [x] pow2 - [x]...

xe: sdpa: fix memory leak in internal sdpa tests

1

# Description This PR fixes a memory leak in the double_and_resize function in the internal tests.

xe: sdpa: Select SDPA config using scoring criteria

6

# Description This PR adds a scoring function to the SDPA primitive that to identify the correct config given an input query. This pull request refactors the configuration selection logic...