ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : do not crash if there is no CPU backend (#13395)

Browse source 
* llama : do not crash if there is no CPU backend

* add checks to examples
This commit is contained in:
Diego Devesa 2025-05-09 13:02:07 +02:00 • committed by GitHub
parent 5c86c9ed3e
commit 27ebfcacba
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 48 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tools/mtmd/llava.cpp
View file

@ -212,6 +212,7 @@ static bool clip_llava_handle_patches(clip_ctx * ctx_clip, std::vector<float *>
ggml_build_forward_expand(gf, flatten);
ggml_backend_ptr backend { ggml_backend_init_by_type(GGML_BACKEND_DEVICE_TYPE_CPU, nullptr) };
GGML_ASSERT(backend != nullptr && "failed to initialize CPU backend");
ggml_backend_graph_compute(backend.get(), gf);
struct ggml_tensor* result = ggml_graph_node(gf, -1);