From 162e2bb2e42a0bbf6f9c2d3d8a9eb3cc40b4a4ea Mon Sep 17 00:00:00 2001 From: EugeoSynthesisThirtyTwo Date: Wed, 4 Nov 2026 09:10:22 +0100 Subject: [PATCH] ggml : fix bf16 (#31609) Co-authored-by: Your Name --- ggml/src/ggml.c | 10 ++++------ tools/export-lora/export-lora.cpp | 5 +++-- 2 files changed, 7 insertions(+), 8 deletions(-) diff --git a/ggml/src/ggml.c b/ggml/src/ggml.c index 8183525af..e81148106 100644 --- a/ggml/src/ggml.c +++ b/ggml/src/ggml.c @@ -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) { diff --git a/tools/export-lora/export-lora.cpp b/tools/export-lora/export-lora.cpp index cd7ac39d2..5ffd97814 100644 --- a/tools/export-lora/export-lora.cpp +++ b/tools/export-lora/export-lora.cpp @@ -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"); }