mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-11 16:26:59 +00:00
llama: update vendored code to commit 40c6d79f (#7875)
This commit is contained in:
71
llama/llava.cpp
vendored
71
llama/llava.cpp
vendored
@@ -1,5 +1,5 @@
|
||||
/**
|
||||
* llama.cpp - commit 3f1ae2e32cde00c39b96be6d01c2997c29bae555 - do not edit this file
|
||||
* llama.cpp - commit 40c6d79fb52f995f47507fedfeaae2ac05d9b35c - do not edit this file
|
||||
*
|
||||
* MIT License
|
||||
*
|
||||
@@ -37,13 +37,17 @@
|
||||
#include <limits>
|
||||
#include <vector>
|
||||
|
||||
#define die(msg) do { fputs("error: " msg "\n", stderr); exit(1); } while (0)
|
||||
#define die_fmt(fmt, ...) do { fprintf(stderr, "error: " fmt "\n", __VA_ARGS__); exit(1); } while (0)
|
||||
|
||||
#define LOG_INF(...) do { fprintf(stdout, __VA_ARGS__); } while (0)
|
||||
#define LOG_WRN(...) do { fprintf(stderr, __VA_ARGS__); } while (0)
|
||||
#define LOG_ERR(...) do { fprintf(stderr, __VA_ARGS__); } while (0)
|
||||
#define LOG_DBG(...) do { fprintf(stdout, __VA_ARGS__); } while (0)
|
||||
#if defined(LLAVA_LOG_OFF)
|
||||
# define LOG_INF(...)
|
||||
# define LOG_WRN(...)
|
||||
# define LOG_ERR(...)
|
||||
# define LOG_DBG(...)
|
||||
#else // defined(LLAVA_LOG_OFF)
|
||||
# define LOG_INF(...) do { fprintf(stdout, __VA_ARGS__); } while (0)
|
||||
# define LOG_WRN(...) do { fprintf(stderr, __VA_ARGS__); } while (0)
|
||||
# define LOG_ERR(...) do { fprintf(stderr, __VA_ARGS__); } while (0)
|
||||
# define LOG_DBG(...) do { fprintf(stdout, __VA_ARGS__); } while (0)
|
||||
#endif // defined(LLAVA_LOG_OFF)
|
||||
|
||||
// RGB uint8 image
|
||||
struct clip_image_u8 {
|
||||
@@ -427,6 +431,40 @@ bool llava_image_embed_make_with_clip_img(clip_ctx * ctx_clip, int n_threads, co
|
||||
return true;
|
||||
}
|
||||
|
||||
struct llava_embd_batch {
|
||||
std::vector<llama_pos> pos;
|
||||
std::vector<int32_t> n_seq_id;
|
||||
std::vector<llama_seq_id> seq_id_0;
|
||||
std::vector<llama_seq_id *> seq_ids;
|
||||
std::vector<int8_t> logits;
|
||||
llama_batch batch;
|
||||
llava_embd_batch(float * embd, int32_t n_embd, int32_t n_tokens, llama_pos pos_0, llama_seq_id seq_id) {
|
||||
pos .resize(n_tokens);
|
||||
n_seq_id.resize(n_tokens);
|
||||
seq_ids .resize(n_tokens + 1);
|
||||
logits .resize(n_tokens);
|
||||
seq_id_0.resize(1);
|
||||
seq_id_0[0] = seq_id;
|
||||
seq_ids [n_tokens] = nullptr;
|
||||
batch = {
|
||||
/*n_tokens =*/ n_tokens,
|
||||
/*tokens =*/ nullptr,
|
||||
/*embd =*/ embd,
|
||||
/*n_embd =*/ n_embd,
|
||||
/*pos =*/ pos.data(),
|
||||
/*n_seq_id =*/ n_seq_id.data(),
|
||||
/*seq_id =*/ seq_ids.data(),
|
||||
/*logits =*/ logits.data(),
|
||||
};
|
||||
for (int i = 0; i < n_tokens; i++) {
|
||||
batch.pos [i] = pos_0 + i;
|
||||
batch.n_seq_id[i] = 1;
|
||||
batch.seq_id [i] = seq_id_0.data();
|
||||
batch.logits [i] = false;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
bool llava_eval_image_embed(llama_context * ctx_llama, const struct llava_image_embed * image_embed, int n_batch, int * n_past) {
|
||||
int n_embd = llama_n_embd(llama_get_model(ctx_llama));
|
||||
|
||||
@@ -435,8 +473,9 @@ bool llava_eval_image_embed(llama_context * ctx_llama, const struct llava_image_
|
||||
if (n_eval > n_batch) {
|
||||
n_eval = n_batch;
|
||||
}
|
||||
llama_batch batch = {int32_t(n_eval), nullptr, (image_embed->embed+i*n_embd), n_embd, nullptr, nullptr, nullptr, nullptr, *n_past, 1, 0, };
|
||||
if (llama_decode(ctx_llama, batch)) {
|
||||
float * embd = image_embed->embed+i*n_embd;
|
||||
llava_embd_batch llava_batch = llava_embd_batch(embd, n_embd, n_eval, *n_past, 0);
|
||||
if (llama_decode(ctx_llama, llava_batch.batch)) {
|
||||
LOG_ERR("%s : failed to eval\n", __func__);
|
||||
return false;
|
||||
}
|
||||
@@ -458,7 +497,7 @@ struct llava_image_embed * llava_image_embed_make_with_bytes(struct clip_ctx * c
|
||||
bool image_embed_result = llava_image_embed_make_with_clip_img(ctx_clip, n_threads, img, &image_embed, &n_image_pos);
|
||||
if (!image_embed_result) {
|
||||
clip_image_u8_free(img);
|
||||
LOG_ERR("%s: coulnd't embed the image\n", __func__);
|
||||
LOG_ERR("%s: couldn't embed the image\n", __func__);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
@@ -490,10 +529,16 @@ static bool load_file_to_bytes(const char* path, unsigned char** bytesOut, long
|
||||
errno = 0;
|
||||
size_t ret = fread(buffer, 1, fileSize, file); // Read the file into the buffer
|
||||
if (ferror(file)) {
|
||||
die_fmt("read error: %s", strerror(errno));
|
||||
LOG_ERR("read error: %s", strerror(errno));
|
||||
free(buffer);
|
||||
fclose(file);
|
||||
return false;
|
||||
}
|
||||
if (ret != (size_t) fileSize) {
|
||||
die("unexpectedly reached end of file");
|
||||
LOG_ERR("unexpectedly reached end of file");
|
||||
free(buffer);
|
||||
fclose(file);
|
||||
return false;
|
||||
}
|
||||
fclose(file); // Close the file
|
||||
|
||||
|
||||
Reference in New Issue
Block a user