[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:
co-authored by
Claude Opus 5
Fadi Arafeh
parent
b3f97dae24
commit
0a6446005d
@@ -71,8 +71,7 @@ class TileGemm82 {
|
||||
scalar_t* __restrict__ curr_m_a = curr_a;
|
||||
vec_op::unroll_loop<int32_t, M>([&](int32_t i) {
|
||||
scalar_t v = *curr_m_a;
|
||||
load_vec_t a_reg_original(v);
|
||||
vec_op::FP32Vec16 a_reg(a_reg_original);
|
||||
vec_op::FP32Vec16 a_reg(static_cast<float>(v));
|
||||
c_regs[i * 2] = c_regs[i * 2] + a_reg * fp32_b_0_reg;
|
||||
c_regs[i * 2 + 1] = c_regs[i * 2 + 1] + a_reg * fp32_b_1_reg;
|
||||
|
||||
|
||||
Reference in New Issue
Block a user