mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-31 08:51:55 +00:00
examples : do not use common library in simple example (#9803)
* examples : do not use common library in simple example * add command line parser, simplify code
This commit is contained in:
Diego Devesa
@@ -1,5 +1,5 @@
|
||||
set(TARGET llama-simple)
|
||||
add_executable(${TARGET} simple.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_11)
|
||||
|
||||
@@ -1,50 +1,112 @@
|
||||
#include "arg.h"
|
||||
#include "common.h"
|
||||
#include "log.h"
|
||||
#include "llama.h"
|
||||
|
||||
#include <cstdio>
|
||||
#include <cstring>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
static void print_usage(int, char ** argv) {
|
||||
LOG("\nexample usage:\n");
|
||||
LOG("\n %s -m model.gguf -p \"Hello my name is\" -n 32\n", argv[0]);
|
||||
LOG("\n");
|
||||
printf("\nexample usage:\n");
|
||||
printf("\n %s -m model.gguf [-n n_predict] [-ngl n_gpu_layers] [prompt]\n", argv[0]);
|
||||
printf("\n");
|
||||
}
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
gpt_params params;
|
||||
// path to the model gguf file
|
||||
std::string model_path;
|
||||
// prompt to generate text from
|
||||
std::string prompt = "Hello my name is";
|
||||
// number of layers to offload to the GPU
|
||||
int ngl = 99;
|
||||
// number of tokens to predict
|
||||
int n_predict = 32;
|
||||
|
||||
params.prompt = "Hello my name is";
|
||||
params.n_predict = 32;
|
||||
// parse command line arguments
|
||||
|
||||
if (!gpt_params_parse(argc, argv, params, LLAMA_EXAMPLE_COMMON, print_usage)) {
|
||||
return 1;
|
||||
{
|
||||
int i = 1;
|
||||
for (; i < argc; i++) {
|
||||
if (strcmp(argv[i], "-m") == 0) {
|
||||
if (i + 1 < argc) {
|
||||
model_path = argv[++i];
|
||||
} else {
|
||||
print_usage(argc, argv);
|
||||
return 1;
|
||||
}
|
||||
} else if (strcmp(argv[i], "-n") == 0) {
|
||||
if (i + 1 < argc) {
|
||||
try {
|
||||
n_predict = std::stoi(argv[++i]);
|
||||
} catch (...) {
|
||||
print_usage(argc, argv);
|
||||
return 1;
|
||||
}
|
||||
} else {
|
||||
print_usage(argc, argv);
|
||||
return 1;
|
||||
}
|
||||
} else if (strcmp(argv[i], "-ngl") == 0) {
|
||||
if (i + 1 < argc) {
|
||||
try {
|
||||
ngl = std::stoi(argv[++i]);
|
||||
} catch (...) {
|
||||
print_usage(argc, argv);
|
||||
return 1;
|
||||
}
|
||||
} else {
|
||||
print_usage(argc, argv);
|
||||
return 1;
|
||||
}
|
||||
} else {
|
||||
// prompt starts here
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (model_path.empty()) {
|
||||
print_usage(argc, argv);
|
||||
return 1;
|
||||
}
|
||||
if (i < argc) {
|
||||
prompt = argv[i++];
|
||||
for (; i < argc; i++) {
|
||||
prompt += " ";
|
||||
prompt += argv[i];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
gpt_init();
|
||||
|
||||
// total length of the sequence including the prompt
|
||||
const int n_predict = params.n_predict;
|
||||
|
||||
// init LLM
|
||||
|
||||
llama_backend_init();
|
||||
llama_numa_init(params.numa);
|
||||
|
||||
// initialize the model
|
||||
|
||||
llama_model_params model_params = llama_model_params_from_gpt_params(params);
|
||||
llama_model_params model_params = llama_model_default_params();
|
||||
model_params.n_gpu_layers = ngl;
|
||||
|
||||
llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
|
||||
llama_model * model = llama_load_model_from_file(model_path.c_str(), model_params);
|
||||
|
||||
if (model == NULL) {
|
||||
fprintf(stderr , "%s: error: unable to load model\n" , __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
// tokenize the prompt
|
||||
|
||||
// find the number of tokens in the prompt
|
||||
const int n_prompt = -llama_tokenize(model, prompt.c_str(), prompt.size(), NULL, 0, true, true);
|
||||
|
||||
// allocate space for the tokens and tokenize the prompt
|
||||
std::vector<llama_token> prompt_tokens(n_prompt);
|
||||
if (llama_tokenize(model, prompt.c_str(), prompt.size(), prompt_tokens.data(), prompt_tokens.size(), true, true) < 0) {
|
||||
fprintf(stderr, "%s: error: failed to tokenize the prompt\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
// initialize the context
|
||||
|
||||
llama_context_params ctx_params = llama_context_params_from_gpt_params(params);
|
||||
llama_context_params ctx_params = llama_context_default_params();
|
||||
// n_ctx is the context size
|
||||
ctx_params.n_ctx = n_prompt + n_predict - 1;
|
||||
// n_batch is the maximum number of tokens that can be processed in a single call to llama_decode
|
||||
ctx_params.n_batch = n_prompt;
|
||||
// enable performance counters
|
||||
ctx_params.no_perf = false;
|
||||
|
||||
llama_context * ctx = llama_new_context_with_model(model, ctx_params);
|
||||
|
||||
@@ -53,117 +115,87 @@ int main(int argc, char ** argv) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
// initialize the sampler
|
||||
|
||||
auto sparams = llama_sampler_chain_default_params();
|
||||
|
||||
sparams.no_perf = false;
|
||||
|
||||
llama_sampler * smpl = llama_sampler_chain_init(sparams);
|
||||
|
||||
llama_sampler_chain_add(smpl, llama_sampler_init_greedy());
|
||||
|
||||
// tokenize the prompt
|
||||
|
||||
std::vector<llama_token> tokens_list;
|
||||
tokens_list = ::llama_tokenize(ctx, params.prompt, true);
|
||||
|
||||
const int n_ctx = llama_n_ctx(ctx);
|
||||
const int n_kv_req = tokens_list.size() + (n_predict - tokens_list.size());
|
||||
|
||||
LOG("\n");
|
||||
LOG_INF("%s: n_predict = %d, n_ctx = %d, n_kv_req = %d\n", __func__, n_predict, n_ctx, n_kv_req);
|
||||
|
||||
// make sure the KV cache is big enough to hold all the prompt and generated tokens
|
||||
if (n_kv_req > n_ctx) {
|
||||
LOG_ERR("%s: error: n_kv_req > n_ctx, the required KV cache size is not big enough\n", __func__);
|
||||
LOG_ERR("%s: either reduce n_predict or increase n_ctx\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
// print the prompt token-by-token
|
||||
|
||||
LOG("\n");
|
||||
|
||||
for (auto id : tokens_list) {
|
||||
LOG("%s", llama_token_to_piece(ctx, id).c_str());
|
||||
for (auto id : prompt_tokens) {
|
||||
char buf[128];
|
||||
int n = llama_token_to_piece(model, id, buf, sizeof(buf), 0, true);
|
||||
if (n < 0) {
|
||||
fprintf(stderr, "%s: error: failed to convert token to piece\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
std::string s(buf, n);
|
||||
printf("%s", s.c_str());
|
||||
}
|
||||
|
||||
// create a llama_batch with size 512
|
||||
// we use this object to submit token data for decoding
|
||||
// prepare a batch for the prompt
|
||||
|
||||
llama_batch batch = llama_batch_init(512, 0, 1);
|
||||
|
||||
// evaluate the initial prompt
|
||||
for (size_t i = 0; i < tokens_list.size(); i++) {
|
||||
llama_batch_add(batch, tokens_list[i], i, { 0 }, false);
|
||||
}
|
||||
|
||||
// llama_decode will output logits only for the last token of the prompt
|
||||
batch.logits[batch.n_tokens - 1] = true;
|
||||
|
||||
if (llama_decode(ctx, batch) != 0) {
|
||||
LOG("%s: llama_decode() failed\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
llama_batch batch = llama_batch_get_one(prompt_tokens.data(), prompt_tokens.size(), 0, 0);
|
||||
|
||||
// main loop
|
||||
|
||||
int n_cur = batch.n_tokens;
|
||||
int n_decode = 0;
|
||||
|
||||
const auto t_main_start = ggml_time_us();
|
||||
int n_decode = 0;
|
||||
llama_token new_token_id;
|
||||
|
||||
for (int n_pos = 0; n_pos + batch.n_tokens < n_prompt + n_predict; ) {
|
||||
// evaluate the current batch with the transformer model
|
||||
if (llama_decode(ctx, batch)) {
|
||||
fprintf(stderr, "%s : failed to eval, return code %d\n", __func__, 1);
|
||||
return 1;
|
||||
}
|
||||
|
||||
n_pos += batch.n_tokens;
|
||||
|
||||
while (n_cur <= n_predict) {
|
||||
// sample the next token
|
||||
{
|
||||
const llama_token new_token_id = llama_sampler_sample(smpl, ctx, -1);
|
||||
new_token_id = llama_sampler_sample(smpl, ctx, -1);
|
||||
|
||||
// is it an end of generation?
|
||||
if (llama_token_is_eog(model, new_token_id) || n_cur == n_predict) {
|
||||
LOG("\n");
|
||||
|
||||
if (llama_token_is_eog(model, new_token_id)) {
|
||||
break;
|
||||
}
|
||||
|
||||
LOG("%s", llama_token_to_piece(ctx, new_token_id).c_str());
|
||||
char buf[128];
|
||||
int n = llama_token_to_piece(model, new_token_id, buf, sizeof(buf), 0, true);
|
||||
if (n < 0) {
|
||||
fprintf(stderr, "%s: error: failed to convert token to piece\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
std::string s(buf, n);
|
||||
printf("%s", s.c_str());
|
||||
fflush(stdout);
|
||||
|
||||
// prepare the next batch
|
||||
llama_batch_clear(batch);
|
||||
|
||||
// push this new token for next evaluation
|
||||
llama_batch_add(batch, new_token_id, n_cur, { 0 }, true);
|
||||
// prepare the next batch with the sampled token
|
||||
batch = llama_batch_get_one(&new_token_id, 1, n_pos, 0);
|
||||
|
||||
n_decode += 1;
|
||||
}
|
||||
|
||||
n_cur += 1;
|
||||
|
||||
// evaluate the current batch with the transformer model
|
||||
if (llama_decode(ctx, batch)) {
|
||||
LOG_ERR("%s : failed to eval, return code %d\n", __func__, 1);
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
||||
LOG("\n");
|
||||
printf("\n");
|
||||
|
||||
const auto t_main_end = ggml_time_us();
|
||||
|
||||
LOG_INF("%s: decoded %d tokens in %.2f s, speed: %.2f t/s\n",
|
||||
fprintf(stderr, "%s: decoded %d tokens in %.2f s, speed: %.2f t/s\n",
|
||||
__func__, n_decode, (t_main_end - t_main_start) / 1000000.0f, n_decode / ((t_main_end - t_main_start) / 1000000.0f));
|
||||
|
||||
LOG("\n");
|
||||
fprintf(stderr, "\n");
|
||||
llama_perf_sampler_print(smpl);
|
||||
llama_perf_context_print(ctx);
|
||||
fprintf(stderr, "\n");
|
||||
|
||||
LOG("\n");
|
||||
|
||||
llama_batch_free(batch);
|
||||
llama_sampler_free(smpl);
|
||||
llama_free(ctx);
|
||||
llama_free_model(model);
|
||||
|
||||
llama_backend_free();
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user