CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix partial offloading for ne0 % 256 != 0 (#8572)

Browse Source
This commit is contained in:
Johannes Gäßler
2024-07-18 23:48:47 +02:00
committed by GitHub
parent 705b7ecf60
commit a15ef8f8a0
4 changed files with 29 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-alloc.c
View File

@@ -776,6 +776,7 @@ bool ggml_gallocr_reserve_n(ggml_gallocr_t galloc, struct ggml_cgraph * graph, c
fprintf(stderr, "%s: failed to allocate %s buffer of size %zu\n", __func__, ggml_backend_buft_name(galloc->bufts[i]), new_size);
return false;
}
ggml_backend_buffer_set_usage(galloc->buffers[i], GGML_BACKEND_BUFFER_USAGE_COMPUTE);
}
}