CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-18 11:46:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

sycl: Add more debug prints (#13640)

Browse Source
This commit is contained in:
Romain Biessy
2025-05-26 10:28:53 +02:00
committed by GitHub
parent fef693dc6b
commit 9012eb9b45
16 changed files with 245 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
ggml/src/ggml-sycl/concat.cpp
View File

@@ -159,39 +159,37 @@ static void concat_f32_sycl_non_cont(
}
void ggml_sycl_op_concat(ggml_backend_sycl_context & ctx, ggml_tensor *dst) {
const ggml_tensor *src0 = dst->src[0];
const ggml_tensor *src1 = dst->src[1];
queue_ptr stream = ctx.stream();
scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/2);
const ggml_tensor * src0 = dst->src[0];
const ggml_tensor * src1 = dst->src[1];
queue_ptr stream = ctx.stream();
const int32_t dim = ((int32_t *)dst->op_params)[0];
const int32_t dim = ((int32_t *) dst->op_params)[0];
if (ggml_is_contiguous(src0) && ggml_is_contiguous(src1)) {
const float *src0_d = (const float *)src0->data;
const float *src1_d = (const float *)src1->data;
if (ggml_is_contiguous(src0) && ggml_is_contiguous(src1)) {
const float * src0_d = (const float *) src0->data;
const float * src1_d = (const float *) src1->data;
float *dst_d = (float *)dst->data;
float * dst_d = (float *) dst->data;
if (dim != 3) {
for (int i3 = 0; i3 < dst->ne[3]; i3++) {
concat_f32_sycl(
src0_d + i3 * (src0->nb[3] / 4), src1_d + i3 * (src1->nb[3] / 4),
dst_d + i3 * (dst->nb[3] / 4), src0->ne[0], src0->ne[1],
src0->ne[2], dst->ne[0], dst->ne[1], dst->ne[2], dim, stream);
}
if (dim != 3) {
for (int i3 = 0; i3 < dst->ne[3]; i3++) {
concat_f32_sycl(src0_d + i3 * (src0->nb[3] / 4), src1_d + i3 * (src1->nb[3] / 4),
dst_d + i3 * (dst->nb[3] / 4), src0->ne[0], src0->ne[1], src0->ne[2], dst->ne[0],
dst->ne[1], dst->ne[2], dim, stream);
}
} else {
const size_t size0 = ggml_nbytes(src0);
const size_t size1 = ggml_nbytes(src1);
SYCL_CHECK(CHECK_TRY_ERROR(stream->memcpy(dst_d, src0_d, size0).wait()));
SYCL_CHECK(CHECK_TRY_ERROR(stream->memcpy(dst_d + size0 / 4, src1_d, size1).wait()));
}
} else {
const size_t size0 = ggml_nbytes(src0);
const size_t size1 = ggml_nbytes(src1);
SYCL_CHECK(CHECK_TRY_ERROR(stream->memcpy(dst_d, src0_d, size0).wait()));
SYCL_CHECK(CHECK_TRY_ERROR(
stream->memcpy(dst_d + size0 / 4, src1_d, size1).wait()));
concat_f32_sycl_non_cont(stream, (const char *) src0->data, (const char *) src1->data, (char *) dst->data,
src0->ne[0], src0->ne[1], src0->ne[2], src0->ne[3], src0->nb[0], src0->nb[1],
src0->nb[2], src0->nb[3], src1->ne[0], src1->ne[1], src1->ne[2], src1->ne[3],
src1->nb[0], src1->nb[1], src1->nb[2], src1->nb[3], dst->ne[0], dst->ne[1], dst->ne[2],
dst->ne[3], dst->nb[0], dst->nb[1], dst->nb[2], dst->nb[3], dim);
}
} else
concat_f32_sycl_non_cont(
stream, (const char *)src0->data, (const char *)src1->data,
(char *)dst->data, src0->ne[0], src0->ne[1], src0->ne[2], src0->ne[3],
src0->nb[0], src0->nb[1], src0->nb[2], src0->nb[3], src1->ne[0],
src1->ne[1], src1->ne[2], src1->ne[3], src1->nb[0], src1->nb[1],
src1->nb[2], src1->nb[3], dst->ne[0], dst->ne[1], dst->ne[2],
dst->ne[3], dst->nb[0], dst->nb[1], dst->nb[2], dst->nb[3], dim);
}