[Hardware][Power] Enable W4A16 (AWQ & GPTQ) quantization on POWER10 using VSX (#59149)

Signed-off-by: Rukhaiya <bibirukhaiya123@gmail.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
Rukhaiya2004
2026-09-30 19:44:48 +08:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent 863475eb9c
commit 72e7874fa6
7 changed files with 99 additions and 9 deletions
+31 -2
View File
@@ -7,6 +7,9 @@
#if defined(__riscv_v)
#include "cpu/micro_gemm/cpu_micro_gemm_rvv.hpp"
#endif
#if defined(__powerpc__)
#include "cpu/micro_gemm/cpu_micro_gemm_vsx.hpp"
#endif
#include "cpu/micro_gemm/cpu_micro_gemm_vec.hpp"
#define VLLM_DISPATCH_CASE_16B_TYPES(...) \
@@ -104,8 +107,8 @@ class Dequantizer4b {
scalar_vec_t output_vec_0(wb_0);
scalar_vec_t output_vec_1(wb_1);
// AMX needs to interleave K elements to pack as 32 bits
if constexpr (isa == ISA::AMX) {
// AMX and VSX need to interleave K elements to pack as 32 bits
if constexpr (isa == ISA::AMX || isa == ISA::VSX) {
vec_op::interleave_save(output_vec_0, output_vec_1, curr_weight);
} else {
output_vec_0.save(curr_weight);
@@ -303,6 +306,8 @@ void cpu_gemm_wna16(
return ISA::VEC;
} else if (isa_hint == "rvv") {
return ISA::RVV;
} else if (isa_hint == "vsx") {
return ISA::VSX;
} else {
TORCH_CHECK(false, "unsupported isa hint: " + isa_hint);
}
@@ -378,6 +383,30 @@ void cpu_gemm_wna16(
scales_group_stride, zeros_group_stride, group_size, pack_factor);
return;
}
} else if (isa == ISA::VSX) {
TORCH_CHECK(input.scalar_type() == at::ScalarType::BFloat16,
"VSX WNA16 GEMM only supports BFloat16");
using gemm_t = cpu_micro_gemm::MicroGemm<ISA::VSX, scalar_t>;
if (has_zp) {
using dequantizer_t = Dequantizer4b<scalar_t, ISA::VSX, true>;
cpu_gemm_wna16_impl<scalar_t, dequantizer_t, gemm_t>(
input.data_ptr<scalar_t>(), q_weight.data_ptr<int32_t>(),
output.data_ptr<scalar_t>(), scales.data_ptr<scalar_t>(), zeros_ptr,
bias.has_value() ? bias->data_ptr<scalar_t>() : nullptr, a_m_size,
b_n_size, a_k_size, a_m_stride, output_m_stride,
scales_group_stride, zeros_group_stride, group_size, pack_factor);
return;
}
{
using dequantizer_t = Dequantizer4b<scalar_t, ISA::VSX, false>;
cpu_gemm_wna16_impl<scalar_t, dequantizer_t, gemm_t>(
input.data_ptr<scalar_t>(), q_weight.data_ptr<int32_t>(),
output.data_ptr<scalar_t>(), scales.data_ptr<scalar_t>(), zeros_ptr,
bias.has_value() ? bias->data_ptr<scalar_t>() : nullptr, a_m_size,
b_n_size, a_k_size, a_m_stride, output_m_stride,
scales_group_stride, zeros_group_stride, group_size, pack_factor);
return;
}
}
});
}