Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

Revert "[SYCL] fallback mmvq (#9088)" (#9579)

Browse Source 
This reverts commit 50addec9a5.
This commit is contained in:
Akarshan Biswas 2024-09-23 08:58:06 +05:30 committed by GitHub
parent c35e586ea5
commit e62e9789cd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-sycl.cpp
View File

@ -3496,8 +3496,7 @@ static void ggml_sycl_mul_mat(ggml_backend_sycl_context & ctx, const ggml_tensor
bool use_mul_mat_vec_q = ggml_is_quantized(src0->type)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
&& src1->ne[1] <= MMVQ_MAX_BATCH_SIZE
&& (ctx.stream()->get_backend() == sycl::backend::ext_oneapi_cuda || src1->ne[1] > MMVQ_MIN_BATCH_SIZE);
&& src1->ne[1] <= MMVQ_MAX_BATCH_SIZE;
bool use_mul_mat_q = ggml_sycl_supports_mmq(src0->type)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32;

1
ggml/src/ggml-sycl/common.hpp
View File

@ -134,7 +134,6 @@ typedef sycl::float2 dfloat2;
#endif // GGML_SYCL_F16
#define MMVQ_MAX_BATCH_SIZE 8
#define MMVQ_MIN_BATCH_SIZE 4
static const int8_t kvalues_iq4nl[16]={-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113};