EngineX-Mthreads/enginex-mthreads-llama.cpp
4
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Sync from upstream llama.cpp repository

Browse Source
This commit is contained in:
xiezhongtao
2026-01-16 10:43:34 +08:00
parent 3bc369a6f7
commit f4ae4cc7da
2053 changed files with 956010 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
examples/simple/CMakeLists.txt Normal file
View File

@@ -0,0 +1,5 @@
set(TARGET llama-simple)
add_executable(${TARGET} simple.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE llama ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_17)

21
examples/simple/README.md Normal file
View File

@@ -0,0 +1,21 @@
# llama.cpp/example/simple
The purpose of this example is to demonstrate a minimal usage of llama.cpp for generating text with a given prompt.
```bash
./llama-simple -m ./models/llama-7b-v2/ggml-model-f16.gguf "Hello my name is"
...
main: n_len = 32, n_ctx = 2048, n_parallel = 1, n_kv_req = 32
Hello my name is Shawn and I'm a 20 year old male from the United States. I'm a 20 year old
main: decoded 27 tokens in 2.31 s, speed: 11.68 t/s
llama_print_timings: load time = 579.15 ms
llama_print_timings: sample time = 0.72 ms / 28 runs ( 0.03 ms per token, 38888.89 tokens per second)
llama_print_timings: prompt eval time = 655.63 ms / 10 tokens ( 65.56 ms per token, 15.25 tokens per second)
llama_print_timings: eval time = 2180.97 ms / 27 runs ( 80.78 ms per token, 12.38 tokens per second)
llama_print_timings: total time = 2891.13 ms
```

220
examples/simple/simple.cpp Normal file
View File

@@ -0,0 +1,220 @@
#include "llama.h"
#include <cstdio>
#include <cstring>
#include <string>
#include <vector>
static void print_usage(int, char ** argv) {
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) {
// 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;
// parse command line arguments
{
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];
}
}
}
// load dynamic backends
ggml_backend_load_all();
// initialize the model
llama_model_params model_params = llama_model_default_params();
model_params.n_gpu_layers = ngl;
llama_model * model = llama_model_load_from_file(model_path.c_str(), model_params);
if (model == NULL) {
fprintf(stderr , "%s: error: unable to load model\n" , __func__);
return 1;
}
const llama_vocab * vocab = llama_model_get_vocab(model);
// tokenize the prompt
// find the number of tokens in the prompt
const int n_prompt = -llama_tokenize(vocab, 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(vocab, 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_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_init_from_model(model, ctx_params);
if (ctx == NULL) {
fprintf(stderr , "%s: error: failed to create the llama_context\n" , __func__);
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());
// print the prompt token-by-token
for (auto id : prompt_tokens) {
char buf[128];
int n = llama_token_to_piece(vocab, 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());
}
// prepare a batch for the prompt
llama_batch batch = llama_batch_get_one(prompt_tokens.data(), prompt_tokens.size());
if (llama_model_has_encoder(model)) {
if (llama_encode(ctx, batch)) {
fprintf(stderr, "%s : failed to eval\n", __func__);
return 1;
}
llama_token decoder_start_token_id = llama_model_decoder_start_token(model);
if (decoder_start_token_id == LLAMA_TOKEN_NULL) {
decoder_start_token_id = llama_vocab_bos(vocab);
}
batch = llama_batch_get_one(&decoder_start_token_id, 1);
}
// main loop
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;
// sample the next token
{
new_token_id = llama_sampler_sample(smpl, ctx, -1);
// is it an end of generation?
if (llama_vocab_is_eog(vocab, new_token_id)) {
break;
}
char buf[128];
int n = llama_token_to_piece(vocab, 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 with the sampled token
batch = llama_batch_get_one(&new_token_id, 1);
n_decode += 1;
}
}
printf("\n");
const auto t_main_end = ggml_time_us();
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));
fprintf(stderr, "\n");
llama_perf_sampler_print(smpl);
llama_perf_context_print(ctx);
fprintf(stderr, "\n");
llama_sampler_free(smpl);
llama_free(ctx);
llama_model_free(model);
return 0;
}