[CPU] Migrate unquantized MoE to the modular-kernel experts structure (#50133)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
This commit is contained in:
Li, Jiang
2026-08-03 14:55:04 +08:00
committed by GitHub
co-authored by Claude Opus 5 Fadi Arafeh
parent b3f97dae24
commit 0a6446005d
20 changed files with 972 additions and 839 deletions
-2
View File
@@ -40,12 +40,10 @@ struct VecTypeTrait<c10::BFloat16> {
using vec_t = vec_op::BF16Vec16;
};
#if !defined(__powerpc__)
template <>
struct VecTypeTrait<c10::Half> {
using vec_t = vec_op::FP16Vec16;
};
#endif
struct Counter {
std::atomic<int64_t> counter;