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

re-enabled mul_mat_batched_sycl path for batched Q*K & KQ*V

Browse source
This commit is contained in:
OuadiElfarouki 2024-06-21 17:50:28 +01:00
parent 0e4699e651
commit 65a9c9bac6
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-sycl.cpp
View file

@ -15228,7 +15228,7 @@ static void ggml_sycl_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1
} else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_contiguous(src0) && !ggml_is_transposed(src1) && src1->ne[1] == 1) { } else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_contiguous(src0) && !ggml_is_transposed(src1) && src1->ne[1] == 1) {
// KQV single-batch // KQV single-batch
ggml_sycl_mul_mat_vec_nc(src0, src1, dst); ggml_sycl_mul_mat_vec_nc(src0, src1, dst);
} else if (!split && src0->type == GGML_TYPE_F16 && (src1->type == GGML_TYPE_F16) && !ggml_is_transposed(src0) && !ggml_is_transposed(src1) && src1->ne[2]*src1->ne[3] > 1) { } else if (!split && src0->type == GGML_TYPE_F16 && !ggml_is_transposed(src0) && !ggml_is_transposed(src1) && src1->ne[2] * src1->ne[3] > 1) {
// KQ + KQV multi-batch // KQ + KQV multi-batch
ggml_sycl_mul_mat_batched_sycl(src0, src1, dst); ggml_sycl_mul_mat_batched_sycl(src0, src1, dst);
} else if (use_dequantize_mul_mat_vec) { } else if (use_dequantize_mul_mat_vec) {