Merge commit '533b18257b7da879a5de39f5d6437041e0e42c39' into concedo_experimental

# Conflicts:
#	CMakeLists.txt
#	examples/gguf-hash/CMakeLists.txt
#	examples/gguf-hash/gguf-hash.cpp
#	scripts/sync_vendor.py
#	tools/mtmd/CMakeLists.txt
#	vendor/hash/rotate-bits/rotate-bits.h
#	vendor/hash/sha1/sha1.c
#	vendor/hash/sha1/sha1.h
#	vendor/hash/sha256/sha256.c
#	vendor/hash/sha256/sha256.h
#	vendor/hash/xxhash/xxhash.c
#	vendor/hash/xxhash/xxhash.h
This commit is contained in:
Concedo
2026-08-20 18:42:18 +08:00
28 changed files with 8000 additions and 40 deletions
+4 -13
View File
@@ -12,6 +12,8 @@
#include "mtmd-helper-common.h"
#include "llama.h"
#include "vendor/hash/hash.h"
#include <algorithm>
#include <cinttypes>
#include <vector>
@@ -357,25 +359,14 @@ static bool decode_audio_from_buf(const unsigned char * buf_in, size_t len, int
} // namespace audio_helpers
// Computes FNV-1a hash of the data
static std::string fnv_hash(const uint8_t * data, size_t len) {
const uint64_t fnv_prime = 0x100000001b3ULL;
uint64_t hash = 0xcbf29ce484222325ULL;
for (size_t i = 0; i < len; ++i) {
hash ^= data[i];
hash *= fnv_prime;
}
return std::to_string(hash);
}
mtmd_helper_bitmap_wrapper mtmd_helper_bitmap_init_from_buf(mtmd_context * ctx, const unsigned char * buf, size_t len, bool placeholder) {
// calculate the hash if needed
std::string id;
mtmd_bitmap * result = nullptr;
if (!placeholder) {
id = fnv_hash(buf, len);
// use sha256 to prevent cache poisoning
id = hash_sha256_hex(buf, len);
}
if (audio_helpers::is_audio_file((const char *)buf, len)) {