ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2024-12-19 04:37:51 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

ggml: add support for float16 input tensors in pooling operations (ggml/895)

Browse Source 
* Add support for float16 tensors in 1d pooling operations

* Add support for float16 input tensors in 2d pooling operations

* code cleanup

remove unnecessary casting during srow ptr initialization

---------

Co-authored-by: vanaka11 <vanaka1189@gmail.com>
This commit is contained in:
Ivan Filipov 2024-07-22 14:32:02 +03:00 committed by Georgi Gerganov
parent 8da6fd4dff
commit b2ead7d6f4
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
ggml/src/ggml.c
View File

@ -14579,7 +14579,7 @@ static void ggml_compute_forward_pool_1d_sk_p0(
const struct ggml_tensor * src = dst->src[0];
assert(src->type == GGML_TYPE_F32);
assert(src->type == GGML_TYPE_F32 || src->type == GGML_TYPE_F16);
if (params->ith != 0) {
return;
@ -14592,10 +14592,8 @@ static void ggml_compute_forward_pool_1d_sk_p0(
const int64_t rs = dst->ne[0];
while (cdata < data_end) {
const float * const srow = (const float *)cdata;
const void * srow = (const void *)cdata;
int j = 0;
for (int64_t i = 0; i < rs; ++i) {
switch (op) {
case GGML_OP_POOL_AVG: drow[i] = 0; break;
@ -14603,10 +14601,11 @@ static void ggml_compute_forward_pool_1d_sk_p0(
case GGML_OP_POOL_COUNT: GGML_ASSERT(false); break;
}
for (int ki = 0; ki < k; ++ki) {
const float srow_j = (src->type == GGML_TYPE_F32) ? ((const float*)srow)[j] : GGML_FP16_TO_FP32(((const ggml_fp16_t*)srow)[j]);
switch (op) {
case GGML_OP_POOL_AVG: drow[i] += srow[j]; break;
case GGML_OP_POOL_MAX: if (srow[j] > drow[i]) drow[i] = srow[j]; break;
case GGML_OP_POOL_COUNT: GGML_ASSERT(false); break;
case GGML_OP_POOL_AVG: drow[i] += srow_j; break;
case GGML_OP_POOL_MAX: if (srow_j > drow[i]) drow[i] = srow_j; break;
case GGML_OP_POOL_COUNT: GGML_ASSERT(false); break;
}
++j;
}
@ -14647,7 +14646,7 @@ static void ggml_compute_forward_pool_2d(
const struct ggml_tensor * src = dst->src[0];
GGML_ASSERT(src->type == GGML_TYPE_F32);
assert(src->type == GGML_TYPE_F32 || src->type == GGML_TYPE_F16);
if (params->ith != 0) {
return;
@ -14690,14 +14689,15 @@ static void ggml_compute_forward_pool_2d(
for (int ky = 0; ky < k1; ++ky) {
if (iy + ky < 0 || iy + ky >= src->ne[1]) continue;
const float * const srow = (const float *)(cdata + src->nb[1] * (iy + ky));
const void * srow = (const void *)(cdata + src->nb[1] * (iy + ky));
for (int kx = 0; kx < k0; ++kx) {
int j = ix + kx;
if (j < 0 || j >= src->ne[0]) continue;
const float srow_j = (src->type == GGML_TYPE_F32) ? ((const float*)srow)[j] : GGML_FP16_TO_FP32(((const ggml_fp16_t*)srow)[j]);
switch (op) {
case GGML_OP_POOL_AVG: *out += srow[j]; break;
case GGML_OP_POOL_MAX: if (srow[j] > *out) *out = srow[j]; break;
case GGML_OP_POOL_COUNT: GGML_ASSERT(false); break;
case GGML_OP_POOL_AVG: *out += srow_j; break;
case GGML_OP_POOL_MAX: if (srow_j > *out) *out = srow_j; break;
case GGML_OP_POOL_COUNT: GGML_ASSERT(false); break;
}
}
}