mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 10:24:35 +00:00
opencl : fix a bug in ggml_cl_pool_malloc() for ggml_cl_mul_mat_f32() (#2955)
Co-authored-by: Wentai Zhang <wentaizhang@tencent.com>
This commit is contained in:
parent
ca82cf7bac
commit
6460f758db
@ -1493,7 +1493,7 @@ static void ggml_cl_mul_mat_f32(const ggml_tensor * src0, const ggml_tensor * sr
|
||||
if (src0->backend == GGML_BACKEND_GPU) { // NOLINT
|
||||
d_X = (cl_mem) src0->data;
|
||||
} else {
|
||||
d_X = ggml_cl_pool_malloc(sizeof(ggml_fp16_t) * x_ne, &x_size);
|
||||
d_X = ggml_cl_pool_malloc(sizeof(float) * x_ne, &x_size);
|
||||
}
|
||||
cl_mem d_Y = ggml_cl_pool_malloc(sizeof(float) * y_ne, &y_size);
|
||||
cl_mem d_D = ggml_cl_pool_malloc(sizeof(float) * d_ne, &d_size);
|
||||
|
Loading…
Reference in New Issue
Block a user