tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

sycl: quantize and reorder the input to q8_1 when reorder is enabled (#13826)

Browse Source 
* [WIP]: fuse q8 quantization and reorder

* wip2: fuse q8 quantization and reorder

* working q8 reorder commit

* restored common.hpp

* remove debug prints

* remove unnecessary headers and remove trailing whitespace

* Update ggml/src/ggml-sycl/ggml-sycl.cpp

Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@intel.com>

---------

Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@intel.com>
This commit is contained in:
Atharva Dubey
2025-06-02 10:12:20 +01:00
committed by GitHub
parent 7675c555a1
commit 663445b0de
3 changed files with 120 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
ggml/src/ggml-sycl/vecdotq.hpp
View File

@@ -285,21 +285,21 @@ template <> struct reorder_vec_dot_q_sycl<GGML_TYPE_Q4_0> {
}
__dpct_inline__ float operator()(const void * __restrict__ vbq, const int ibx_offset, const int d_offset,
const block_q8_1 * __restrict__ bq8_1, const int & iqs, int /* nblocks */) {
const int8_t* q8_1_quant_ptr, const sycl::half2* q8_1_ds, const int & iqs, int /* nblocks */) {
const uint8_t * bq4_0 = static_cast<const uint8_t *>(vbq) + ibx_offset;
const ggml_half d = *(reinterpret_cast<const ggml_half *>(static_cast<const uint8_t *>(vbq) + d_offset));
int v[q4_0_traits::vdr_mmvq];
int u[2 * q4_0_traits::vdr_mmvq];
#pragma unroll
#pragma unroll
for (size_t i = 0; i < q4_0_traits::vdr_mmvq; ++i) {
v[i] = get_int_from_uint8(bq4_0, iqs + i);
u[2 * i + 0] = get_int_from_int8_aligned(bq8_1->qs, iqs + i);
u[2 * i + 1] = get_int_from_int8_aligned(bq8_1->qs, iqs + i + q4_0_traits::qi);
u[2 * i + 0] = get_int_from_int8_aligned(q8_1_quant_ptr, iqs + i);
u[2 * i + 1] = get_int_from_int8_aligned(q8_1_quant_ptr, iqs + i + q4_0_traits::qi);
}
return vec_dot_q4_0_q8_1_impl(v, u, d, bq8_1->ds);
return vec_dot_q4_0_q8_1_impl(v, u, d, *q8_1_ds);
};
};
@@ -347,7 +347,7 @@ template <> struct reorder_vec_dot_q_sycl<GGML_TYPE_Q4_K> {
using q4_k_traits = typename q4_k_block::traits;
float operator()(const void * __restrict__ vbq, const int ibx_offset, const int d_offset,
const block_q8_1 * __restrict__ bq8_1, const int & iqs, int nblocks) {
const int8_t* q8_1_quant_ptr, const sycl::half2* q8_1_ds, const int & iqs, int nblocks) {
const int ib = ibx_offset / (QK_K / 2);
const uint8_t * base = static_cast<const uint8_t *>(vbq);
@@ -360,7 +360,38 @@ template <> struct reorder_vec_dot_q_sycl<GGML_TYPE_Q4_K> {
const int * q4 = (const int *) (qs + 16 * bq8_offset + 4 * ((iqs / 2) % 4));
const uint16_t * scales = (const uint16_t *) scs;
return vec_dot_q4_K_q8_1_common(q4, scales, *dms, bq8_1, iqs);
int v[2];
int u[2 * QR4_K];
float d8[QR4_K];
v[0] = q4[0];
v[1] = q4[4];
uint16_t aux[2];
const int j = (QR4_K * ((iqs / 2) / (QI8_1 / 2))) / 2;
if (j < 2) {
aux[0] = scales[j + 0] & 0x3f3f;
aux[1] = scales[j + 2] & 0x3f3f;
} else {
aux[0] = ((scales[j + 2] >> 0) & 0x0f0f) | ((scales[j - 2] & 0xc0c0) >> 2);
aux[1] = ((scales[j + 2] >> 4) & 0x0f0f) | ((scales[j - 0] & 0xc0c0) >> 2);
}
const uint8_t * sc = (const uint8_t *) aux;
const uint8_t * m = sc + 2;
for (int i = 0; i < QR4_K; ++i) {
const int8_t* quant_base_ptr = q8_1_quant_ptr + (bq8_offset + i) * QK8_1;
sycl::half2 ds_values = *(q8_1_ds + bq8_offset + i);
d8[i] = ds_values[0];
const int * q8 = (const int *) quant_base_ptr + ((iqs / 2) % 4);
u[2 * i + 0] = q8[0];
u[2 * i + 1] = q8[4];
}
return vec_dot_q4_K_q8_1_impl_vmmq(v, u, sc, m, *dms, d8);
}
};