Enable explicitly vectorized `_weight_int8pack_mm` op for FP16 dtype on x86_64 CPU#146777

Open

sanchitintel wants to merge 6 commits intomainfrom

sanchitintel/refactor_aten_int8_woq_gemm

Commits on Feb 9, 2025

Use vectorized `_weight_int8pack_mm` on CPU for Half dtype as well
sanchitintel
authored

Commits on Feb 10, 2025

Commits on Feb 11, 2025

Modify another UT to support FP16
sanchitintel
authored

Commits on Feb 25, 2025

Merge branch 'main' into sanchitintel/refactor_aten_int8_woq_gemm
sanchitintel
authored