vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
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;