1 parent
6900fb5ac8
commit
162e2bb2e4
2 files changed
+7
-8
No files matched your search
+4
-6
@@ -485,27 +485,25 @@ void ggml_fp16_to_fp32_row(const ggml_fp16_t * x, float * y, int64_t n) {
|
||||
}
|
||||
|
||||
void ggml_fp32_to_fp16_row(const float * x, ggml_fp16_t * y, int64_t n) {
|
||||
int i = 0;
|
||||
for (; i < n; ++i) {
|
||||
for (int64_t i = 0; i < n; i++) {
|
||||
y[i] = GGML_FP32_TO_FP16(x[i]);
|
||||
}
|
||||
}
|
||||
|
||||
void ggml_bf16_to_fp32_row(const ggml_bf16_t * x, float * y, int64_t n) {
|
||||
int i = 0;
|
||||
for (; i < n; ++i) {
|
||||
for (int64_t i = 0; i < n; i++) {
|
||||
y[i] = GGML_BF16_TO_FP32(x[i]);
|
||||
}
|
||||
}
|
||||
|
||||
void ggml_fp32_to_bf16_row_ref(const float * x, ggml_bf16_t * y, int64_t n) {
|
||||
for (int i = 0; i < n; i++) {
|
||||
for (int64_t i = 0; i < n; i++) {
|
||||
y[i] = ggml_compute_fp32_to_bf16(x[i]);
|
||||
}
|
||||
}
|
||||
|
||||
void ggml_fp32_to_bf16_row(const float * x, ggml_bf16_t * y, int64_t n) {
|
||||
int i = 0;
|
||||
int64_t i = 0;
|
||||
#if defined(__AVX512BF16__)
|
||||
// subnormals are flushed to zero on this platform
|
||||
for (; i + 32 <= n; i += 32) {
|
||||
|
||||
@@ -182,6 +182,8 @@ struct lora_merge_ctx {
|
||||
ggml_type get_out_tensor_type(struct ggml_tensor * t) {
|
||||
if (t->type == GGML_TYPE_F32) {
|
||||
return GGML_TYPE_F32;
|
||||
} else if (t->type == GGML_TYPE_BF16) {
|
||||
return GGML_TYPE_BF16;
|
||||
} else {
|
||||
return GGML_TYPE_F16;
|
||||
}
|
||||
@@ -409,8 +411,7 @@ struct lora_merge_ctx {
|
||||
|
||||
static void print_usage(int, char ** argv) {
|
||||
printf("\nexample usage:\n");
|
||||
printf("\n %s -m base-model.gguf --lora lora-file.gguf -o merged-model-f16.gguf\n", argv[0]);
|
||||
printf("\nNOTE: output model is F16\n");
|
||||
printf("\n %s -m base-model.gguf --lora lora-file.gguf -o merged-model.gguf\n", argv[0]);
|
||||
printf("\n");
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user