public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-09-30 19:41:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

gguf : align the data section relative to the GGUF start, not the file (llama/28993)

Browse Source 
* gguf : align the data section relative to the GGUF start, not the file

gguf_init_from_file_ptr reads a GGUF from the current file position, but padded
the data section from file offset 0, so a GGUF embedded at an offset that is not
a multiple of the alignment loaded without error and returned wrong tensor data.

Also adds llama_adapter_lora_init_from_file_ptr, and disables mmap with a warning
when an embedded data section is not aligned, instead of asserting in ggml.

Assisted-by: Claude Opus 5

* llama : load lora from path through the FILE* variant

The test now checks that mmap is disabled only for an unaligned offset.

Assisted-by: Claude Fable 5.1

* Update ggml/src/gguf.cpp

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update include/llama.h

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* llama : error on unaligned mmap of an embedded GGUF, drop test-load-file-ptr

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Yuri Khrustalev
2026-09-23 20:46:47 +03:00
committed by Georgi Gerganov
co-authored by Johannes Gäßler
parent b9e5f3acb0
commit 78264220d9
1 changed files with 8 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/gguf.cpp
+8 -1
View File
@@ -238,6 +238,7 @@ struct gguf_reader {
: callback(callback),
userdata(userdata),
max_chunk_read(max_chunk_read),
start_offset(data_offset),
data_offset(data_offset),
nbytes_remain(nbytes_remain) {
GGML_ASSERT(max_chunk_read > 0);
@@ -366,6 +367,11 @@ struct gguf_reader {
return data_offset;
}
// position in the file where the GGUF data starts, alignment is relative to it, not to the file
uint64_t start() const {
return start_offset;
}
bool seek(uint64_t absolute_offset) const {
const uint64_t end_offset = uint64_t(data_offset) + nbytes_remain;
if (absolute_offset > end_offset) {
@@ -415,6 +421,7 @@ private:
gguf_reader_callback_t callback = nullptr;
void * userdata = nullptr;
size_t max_chunk_read = 0;
uint64_t start_offset = 0;
mutable uint64_t data_offset = 0;
mutable uint64_t nbytes_remain = 0;
};
@@ -763,7 +770,7 @@ static struct gguf_context * gguf_init_from_reader(const struct gguf_reader & gr
GGML_ASSERT(int64_t(ctx->info.size()) == n_tensors);
// we require the data section to be aligned, so take into account any padding
if (n_tensors > 0 && !gr.seek(GGML_PAD(gr.tell(), ctx->alignment))) {
if (n_tensors > 0 && !gr.seek(gr.start() + GGML_PAD(gr.tell() - gr.start(), ctx->alignment))) {
GGML_LOG_ERROR("%s: failed to seek to beginning of data section\n", __func__);
gguf_free(ctx);
return nullptr;