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

any_pascal fixup

Browse source
This commit is contained in:
JohannesGaessler 2024-02-11 19:04:00 +01:00
parent b1f6fab684
commit a3a46580f7
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-cuda.cu
View file

@ -9932,7 +9932,8 @@ static void ggml_cuda_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1
} }
} }
} else { } else {
min_compute_capability = g_device_caps[g_main_device].cc; min_compute_capability = g_device_caps[g_main_device].cc;
any_pascal_with_slow_fp16 = g_device_caps[g_main_device].cc == 610;
} }
// check data types and tensor shapes for custom matrix multiplication kernels: // check data types and tensor shapes for custom matrix multiplication kernels: