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

Merge pull request #6 from ggerganov/iq2_s

Browse source 
fix build
This commit is contained in:
Abhilash Majumder 2024-03-19 14:07:32 +05:30 • committed by GitHub
commit 7f70fbe227
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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

@ -15617,7 +15617,7 @@ static void ggml_sycl_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1
bool use_dequantize_mul_mat_vec = (ggml_is_quantized(src0->type) || src0->type == GGML_TYPE_F16)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
&& src0->ne[0] % GGML_CUDA_DMMV_X == 0 && src1->ne[1] == 1;
&& src0->ne[0] % GGML_SYCL_DMMV_X == 0 && src1->ne[1] == 1;
bool use_mul_mat_vec_q = min_compute_capability >= VER_4VEC && ggml_is_quantized(src0->type)
&& src1->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32
&& src1->ne[1] <= XMX_MAX_BATCH_SIZE;