diff options
| author | 0cc4m <picard12@live.de> | 2024-06-11 21:20:29 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-11 21:20:29 +0200 |
| commit | ef52d1d16afc695d798396cdd13594ea5e45a9dd (patch) | |
| tree | d6ef7a296ce1df22eb803650da442a1c5ca55340 /ggml-alloc.c | |
| parent | 14f83526cd27f638c856ea6eff08110b9860eb2a (diff) | |
Update Vulkan RoPE implementation (#7818)
* Update Vulkan RoPE implementation
* Return nullptr on alloc_buffer when allocation fails, instead of throwing an exception
Minor fixes
* Fix segfault when running out of VRAM
Co-authored-by: slaren <slarengh@gmail.com>
---------
Co-authored-by: slaren <slarengh@gmail.com>
Diffstat (limited to 'ggml-alloc.c')
| -rw-r--r-- | ggml-alloc.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/ggml-alloc.c b/ggml-alloc.c index 73a3c157..eb75962d 100644 --- a/ggml-alloc.c +++ b/ggml-alloc.c @@ -886,7 +886,7 @@ static bool alloc_tensor_range(struct ggml_context * ctx, fprintf(stderr, "%s: failed to allocate %s buffer of size %zu\n", __func__, ggml_backend_buft_name(buft), size); #endif for (size_t i = 0; i < *n_buffers; i++) { - ggml_backend_buffer_free(*buffers[i]); + ggml_backend_buffer_free((*buffers)[i]); } free(*buffers); return false; |