CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

automatically calculate compute buffer sizes (without graph allocator)

Browse Source
This commit is contained in:
slaren
2023-07-20 02:22:54 +02:00
parent 77ac8deaf1
commit cb205c0d13
5 changed files with 132 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-cuda.cu
View File

@@ -1726,7 +1726,7 @@ static ggml_backend_buffer * ggml_backend_cuda_alloc_buffer(ggml_backend * backe
void * data;
CUDA_CHECK(cudaMalloc(&data, size));
ggml_backend_buffer * buffer = ggml_allocator_simple_init(data, size, TENSOR_ALIGNMENT);
ggml_backend_buffer * buffer = ggml_allocator_default_init(data, size, TENSOR_ALIGNMENT);
buffer->interface.free_data = ggml_backend_cuda_free_buffer;
buffer->backend_data = data;