tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-04 08:15:55 -04:00
Code Issues 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
2 changed files with 3 additions and 1 deletions
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)
&& 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)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32;