extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-01 07:25:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

sycl: disable reorder for sycl mulmat (llama/13536)

Browse Source
This commit is contained in:
Svetlozar Georgiev 2025-05-20 10:34:15 +01:00 committed by Georgi Gerganov
parent e04e8f1c79
commit f44b53480f
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-sycl/ggml-sycl.cpp
View File

@ -3028,7 +3028,7 @@ static bool should_reorder_tensor(ggml_backend_sycl_context& ctx, const ggml_ten
return !g_ggml_sycl_disable_optimize && //allow optimize, controlled by $GGML_SYCL_DISABLE_OPT return !g_ggml_sycl_disable_optimize && //allow optimize, controlled by $GGML_SYCL_DISABLE_OPT
ctx.opt_feature.reorder && //allow this device due to good perf, skip the devices with bad perf. ctx.opt_feature.reorder && //allow this device due to good perf, skip the devices with bad perf.
dst->op == GGML_OP_MUL_MAT && //limit to some supported cases of Q4_0, to do for more cases. dst->op == GGML_OP_MUL_MAT && //limit to some supported cases of Q4_0, to do for more cases.
dst->src[1]->ne[2]==1 && dst->src[1]->ne[3]==1; dst->src[1]->ne[1]==1 && dst->src[1]->ne[2]==1 && dst->src[1]->ne[3]==1;
} }
static void opt_for_reorder(ggml_backend_sycl_context * ctx, const ggml_tensor * src0, const ggml_tensor * /* src1 */, static void opt_for_reorder(ggml_backend_sycl_context * ctx, const ggml_tensor * src0, const ggml_tensor * /* src1 */,
@ -3151,8 +3151,6 @@ static void ggml_sycl_mul_mat(ggml_backend_sycl_context & ctx, const ggml_tensor
ggml_sycl_op_mul_mat(ctx, src0, src1, dst, ggml_sycl_op_mul_mat_q, convert_src1_to_q8_1); ggml_sycl_op_mul_mat(ctx, src0, src1, dst, ggml_sycl_op_mul_mat_q, convert_src1_to_q8_1);
} else { } else {
constexpr bool convert_src1_to_q8_1 = false; constexpr bool convert_src1_to_q8_1 = false;
// MUL_MAT_SYCL supports reorder
opt_for_reorder(&ctx, src0, src1, dst, mul_mat_algo::MUL_MAT_SYCL);
ggml_sycl_op_mul_mat(ctx, src0, src1, dst, ggml_sycl_op_mul_mat_sycl, convert_src1_to_q8_1); ggml_sycl_op_mul_mat(ctx, src0, src1, dst, ggml_sycl_op_mul_mat_sycl, convert_src1_to_q8_1);
} }
GGML_SYCL_DEBUG("call %s done\n", __func__); GGML_SYCL_DEBUG("call %s done\n", __func__);