🌐 AI搜索 & 代理 主页
Skip to content

fix: avoid crash loading LoRAs with bf16 weights #1077

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
leejet merged 1 commit into from
Dec 12, 2025
Merged

fix: avoid crash loading LoRAs with bf16 weights #1077

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion ggml_extend.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1400,10 +1400,14 @@ __STATIC_INLINE__ void ggml_ext_backend_tensor_get_and_sync(ggml_backend_t backe
}

__STATIC_INLINE__ float ggml_ext_backend_tensor_get_f32(ggml_tensor* tensor) {
GGML_ASSERT(tensor->type == GGML_TYPE_F32 || tensor->type == GGML_TYPE_F16 || tensor->type == GGML_TYPE_I32);
GGML_ASSERT(tensor->type == GGML_TYPE_F32 || tensor->type == GGML_TYPE_F16 || tensor->type == GGML_TYPE_I32 || tensor->type == GGML_TYPE_BF16);
float value;
if (tensor->type == GGML_TYPE_F32) {
ggml_backend_tensor_get(tensor, &value, 0, sizeof(value));
} else if (tensor->type == GGML_TYPE_BF16) {
ggml_bf16_t bf16_value;
ggml_backend_tensor_get(tensor, &bf16_value, 0, sizeof(bf16_value));
value = ggml_bf16_to_fp32(bf16_value);
} else if (tensor->type == GGML_TYPE_F16) {
ggml_fp16_t f16_value;
ggml_backend_tensor_get(tensor, &f16_value, 0, sizeof(f16_value));
Expand Down
Loading