CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : upgrade init_tensor API to return a ggml_status (#11854)

Browse Source 
* Upgrade init_tensor API to return a ggml_status

To prepare for an 'abort-free' ggml
(ggml not to abort on OOMs but return a OOM status),
as agreeed with Diego in the ggml repo,
upgrade the init_tensor() and view_init() APIs
to return a ggml_status.

* misc fixes

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
William Tambellini
2025-02-28 05:41:47 -08:00
committed by GitHub
parent c43a3e7996
commit 70680c48e5
16 changed files with 136 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-opencl/ggml-opencl.cpp
View File

@@ -1211,7 +1211,7 @@ static void * ggml_backend_opencl_buffer_get_base(ggml_backend_buffer_t buffer)
GGML_UNUSED(buffer);
}
static void ggml_backend_opencl_buffer_init_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor) {
static enum ggml_status ggml_backend_opencl_buffer_init_tensor(ggml_backend_buffer_t buffer, ggml_tensor * tensor) {
ggml_backend_opencl_buffer_context * ctx = (ggml_backend_opencl_buffer_context *) buffer->context;
ggml_cl2_init(buffer->buft->device);
@@ -1251,6 +1251,7 @@ static void ggml_backend_opencl_buffer_init_tensor(ggml_backend_buffer_t buffer,
tensor->extra = extra;
}
}
return GGML_STATUS_SUCCESS;
}
// The optimized gemm and gemv kernels are used for large matrices without batch.