root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 10:54:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

[SYCL] fallback mmvq (#9088)

Browse Source 
* fallback mmvq to mul_mat

* mmvq in cuda path

* Update ggml/src/ggml-sycl.cpp

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

---------

Co-authored-by: Alberto Cabrera Pérez <alberto.cabrera@codeplay.com>
This commit is contained in:
Meng, Hengyu 2024-08-20 23:50:17 +08:00 committed by GitHub
parent 4f8d19ff17
commit 50addec9a5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -3477,7 +3477,8 @@ 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) bool use_mul_mat_vec_q = ggml_is_quantized(src0->type)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
&& src1->ne[1] <= MMVQ_MAX_BATCH_SIZE; && src1->ne[1] <= MMVQ_MAX_BATCH_SIZE
&& (ctx.stream()->get_backend() == sycl::backend::ext_oneapi_cuda || src1->ne[1] > MMVQ_MIN_BATCH_SIZE);
bool use_mul_mat_q = ggml_sycl_supports_mmq(src0->type) bool use_mul_mat_q = ggml_sycl_supports_mmq(src0->type)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32; && src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32;

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

@ -130,6 +130,7 @@ typedef sycl::float2 dfloat2;
#endif // GGML_SYCL_F16 #endif // GGML_SYCL_F16
#define MMVQ_MAX_BATCH_SIZE 8 #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}; static const int8_t kvalues_iq4nl[16]={-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113};