Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

server: save processed mtmd chunks as placeholder (#27278)

Browse Source
This commit is contained in:
Xuan-Son Nguyen
2026-08-17 21:29:50 +02:00
committed by GitHub
parent ed1c3a20f5
commit 533b18257b
5 changed files with 58 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/mtmd/mtmd.cpp
+32 -14
View File
@@ -2322,23 +2322,12 @@ void mtmd_input_chunk_free(mtmd_input_chunk * chunk) {
}
}
int32_t mtmd_input_chunk_save(const mtmd_input_chunk * chunk, char * out_buf, size_t out_len, size_t * expected_out_len) {
// returns 0 on success
static int32_t mtmd_input_chunk_save_impl(const mtmd_input_chunk * chunk, std::vector<char> & out_buf) {
try {
mtmd_serialization ser(MTMD_SERIALIZATION_VERSION);
chunk->serialize(ser);
if (expected_out_len) {
*expected_out_len = ser.data.size();
}
if (!out_buf) {
// caller is only querying the required size
return 0;
}
if (out_len < ser.data.size()) {
LOG_ERR("%s: out_buf is too small, need %zu bytes, got %zu\n", __func__, ser.data.size(), out_len);
return -1;
}
std::memcpy(out_buf, ser.data.data(), ser.data.size());
out_buf = std::move(ser.data);
return 0;
} catch (const std::exception & e) {
LOG_ERR("%s: %s\n", __func__, e.what());
@@ -2346,6 +2335,35 @@ int32_t mtmd_input_chunk_save(const mtmd_input_chunk * chunk, char * out_buf, si
}
}
mtmd_input_chunk * mtmd_input_chunk_get_placeholder(const mtmd_input_chunk * chunk) {
// this is hacky, but still faster than copy the whole batch data
std::vector<char> buf;
if (mtmd_input_chunk_save_impl(chunk, buf) != 0) {
return nullptr;
}
return mtmd_input_chunk_load(buf.data(), buf.size());
}
int32_t mtmd_input_chunk_save(const mtmd_input_chunk * chunk, char * out_buf, size_t out_len, size_t * expected_out_len) {
std::vector<char> buf;
if (mtmd_input_chunk_save_impl(chunk, buf) != 0) {
return -1;
}
if (expected_out_len) {
*expected_out_len = buf.size();
}
if (!out_buf) {
// caller is only querying the required size
return 0;
}
if (out_len < buf.size()) {
LOG_ERR("%s: out_buf is too small, need %zu bytes, got %zu\n", __func__, buf.size(), out_len);
return -1;
}
std::memcpy(out_buf, buf.data(), buf.size());
return 0;
}
mtmd_input_chunk * mtmd_input_chunk_load(const char * buf, size_t len) {
try {
mtmd_serialization ser(MTMD_SERIALIZATION_VERSION, buf, len);