Load parallel.cpp -f file.txt external prompt file

.gitignore

@@ -28,6 +28,9 @@ build*/
 out/
 tmp/
 
+cmake-all.sh
+cmake_all.sh
+
 models/*
 models-mnt
 

cmake_all.sh

@@ -0,0 +1,6 @@
+cd llama.cpp
+rm -r build
+cmake -B build
+cd build
+cmake --build . --config Release
+cd ..

common/common.cpp

@@ -167,6 +167,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 invalid_param = true;
                 break;
             }
+            // store the external file name in params
+            params.prompt_file = argv[i];
             std::copy(std::istreambuf_iterator<char>(file), std::istreambuf_iterator<char>(), back_inserter(params.prompt));
             if (params.prompt.back() == '\n') {
                 params.prompt.pop_back();

common/common.h

@@ -79,6 +79,7 @@ struct gpt_params {
     std::string model_draft       = "";                              // draft model for speculative decoding
     std::string model_alias       = "unknown"; // model alias
     std::string prompt            = "";
+    std::string prompt_file       = "";  // store the external prompt file name
     std::string path_prompt_cache = "";  // path to file for saving/loading prompt eval state
     std::string input_prefix      = "";  // string to prefix user inputs with
     std::string input_suffix      = "";  // string to suffix user inputs with

examples/jeopardy/README.md

@@ -2,7 +2,7 @@
 
 This is pretty much just a straight port of aigoopy/llm-jeopardy/ with an added graph viewer.
 
-The jeopardy test can be used to compare the fact knowledge of different models and compare them to eachother. This is in contrast to some other tests, which test logical deduction, creativity, writing skills, etc.
+The jeopardy test can be used to compare the fact knowledge of different models and compare them to each other. This is in contrast to some other tests, which test logical deduction, creativity, writing skills, etc.
 
 
 Step 1: Open jeopardy.sh and modify the following:

examples/jeopardy/jeopardy.sh

@@ -1,18 +1,19 @@
 #!/bin/bash
 set -e
 
-MODEL=./models/ggml-vicuna-13b-1.1-q4_0.bin
-MODEL_NAME=Vicuna
+MODEL=./models/llama-2-7b/ggml-model-q4_0.gguf
+MODEL_NAME=Llama2-7b-ggml-q4
 
 # exec options
-prefix="Human: " # Ex. Vicuna uses "Human: "
+prefix="Question: " # Ex. Vicuna uses "Human: "
 opts="--temp 0 -n 80" # additional flags
 nl='
 '
 introduction="You will be playing a game of Jeopardy. Simply answer the question in the correct format (Ex. What is Paris, or Who is George Washington)."
 
 # file options
 question_file=./examples/jeopardy/questions.txt
+# if the required model file doesn't exist, create it; otherwise update it
 touch ./examples/jeopardy/results/$MODEL_NAME.txt
 output_file=./examples/jeopardy/results/$MODEL_NAME.txt
 
@@ -21,7 +22,7 @@ counter=1
 echo 'Running'
 while IFS= read -r question
 do
-  exe_cmd="./main -p "\"$prefix$introduction$nl$prefix$question\"" "$opts" -m ""\"$MODEL\""" >> ""\"$output_file\""
+  exe_cmd="./build/bin/main -p "\"$nl$prefix$question\"" "$opts" -m ""\"$MODEL\""" >> ""\"$output_file\""
   echo $counter
   echo "Current Question: $question"
   eval "$exe_cmd"

examples/parallel/parallel.cpp

@@ -10,6 +10,7 @@
 #include <cstdio>
 #include <string>
 #include <vector>
+#include <ctime>
 
 // trim whitespace from the beginning and end of a string
 static std::string trim(const std::string & str) {
@@ -70,6 +71,26 @@ struct client {
     std::vector<llama_token> tokens_prev;
 };
 
+static void print_date_time() {
+    std::time_t current_time = std::time(nullptr);
+    std::tm* local_time = std::localtime(&current_time);
+    char buffer[80];
+    strftime(buffer, sizeof(buffer), "%Y-%m-%d %H:%M:%S", local_time);
+
+    printf("\n\033[35mrun parameters as at %s\033[0m\n", buffer);
+}
+
+// Define a split string function to ...
+static std::vector<std::string> split_string(const std::string& input, char delimiter) {
+    std::vector<std::string> tokens;
+    std::istringstream stream(input);
+    std::string token;
+    while (std::getline(stream, token, delimiter)) {
+        tokens.push_back(token);
+    }
+    return tokens;
+}
+
 int main(int argc, char ** argv) {
     srand(1234);
 
@@ -104,6 +125,23 @@ int main(int argc, char ** argv) {
     params.logits_all = true;
     std::tie(model, ctx) = llama_init_from_gpt_params(params);
 
+    // load the prompts from an external file if there are any
+    if (params.prompt.empty()) {
+        printf("\n\033[32mNo new questions so proceed with build-in defaults.\033[0m\n");
+    } else {
+        // Output each line of the input params.prompts vector and copy to k_prompts
+        int index = 0;
+        printf("\n\033[32mNow printing the external prompt file %s\033[0m\n\n", params.prompt_file.c_str());
+
+        std::vector<std::string> prompts = split_string(params.prompt, '\n');
+        for (const auto& prompt : prompts) {
+            k_prompts.resize(index + 1);
+            k_prompts[index] = prompt;
+            index++;
+            printf("%3d prompt: %s\n", index, prompt.c_str());
+        }
+    }
+
     fprintf(stderr, "\n\n");
     fflush(stderr);
 
@@ -233,7 +271,7 @@ int main(int argc, char ** argv) {
                     client.n_decoded = 0;
                     client.i_batch   = batch.n_tokens - 1;
 
-                    LOG_TEE("\033[1mClient %3d, seq %4d, started decoding ...\033[0m\n", client.id, client.seq_id);
+                    LOG_TEE("\033[31mClient %3d, seq %4d, started decoding ...\033[0m\n", client.id, client.seq_id);
 
                     g_seq_id += 1;
 
@@ -336,8 +374,8 @@ int main(int argc, char ** argv) {
 
                     const auto t_main_end = ggml_time_us();
 
-                    LOG_TEE("\033[1mClient %3d, seq %4d, prompt %4d t, response %4d t, time %5.2f s, speed %5.2f t/s, cache miss %d \033[0m \n\nInput:    %s\nResponse: %s\n\n",
-                            client.id, client.seq_id, client.n_prompt, client.n_decoded,
+                    LOG_TEE("\033[31mClient %3d, seq %3d/%3d, prompt %4d t, response %4d t, time %5.2f s, speed %5.2f t/s, cache miss %d \033[0m \nInput:    %s\n\033[35mResponse: %s\033[0m\n\n",
+                            client.id, client.seq_id, n_seq, client.n_prompt, client.n_decoded,
                             (t_main_end - client.t_start_prompt) / 1e6,
                             (double) (client.n_prompt + client.n_decoded) / (t_main_end - client.t_start_prompt) * 1e6,
                             n_cache_miss,
@@ -357,13 +395,17 @@ int main(int argc, char ** argv) {
 
     const auto t_main_end = ggml_time_us();
 
-    LOG_TEE("\n\n");
+    print_date_time();
+
+    LOG_TEE("\n%s: n_parallel = %d, n_sequences = %d, cont_batching = %d, system tokens = %d\n", __func__, n_clients, n_seq, cont_batching, n_tokens_system);
+    printf("external prompt file (if any): %s\n\n", params.prompt_file.c_str());
+
     LOG_TEE("Total prompt tokens: %6d, speed: %5.2f t/s\n", n_total_prompt, (double) (n_total_prompt              ) / (t_main_end - t_main_start) * 1e6);
     LOG_TEE("Total gen tokens:    %6d, speed: %5.2f t/s\n", n_total_gen,    (double) (n_total_gen                 ) / (t_main_end - t_main_start) * 1e6);
     LOG_TEE("Total speed (AVG):   %6s  speed: %5.2f t/s\n", "",             (double) (n_total_prompt + n_total_gen) / (t_main_end - t_main_start) * 1e6);
     LOG_TEE("Cache misses:        %6d\n", n_cache_miss);
 
-    LOG_TEE("\n\n");
+    LOG_TEE("\n");
 
     llama_print_timings(ctx);
 

llama.cpp

@@ -7761,14 +7761,14 @@ void llama_print_timings(struct llama_context * ctx) {
     const llama_timings timings = llama_get_timings(ctx);
 
     LLAMA_LOG_INFO("\n");
-    LLAMA_LOG_INFO("%s:        load time = %8.2f ms\n", __func__, timings.t_load_ms);
-    LLAMA_LOG_INFO("%s:      sample time = %8.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
+    LLAMA_LOG_INFO("%s:        load time = %10.2f ms\n", __func__, timings.t_load_ms);
+    LLAMA_LOG_INFO("%s:      sample time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_sample_ms, timings.n_sample, timings.t_sample_ms / timings.n_sample, 1e3 / timings.t_sample_ms * timings.n_sample);
-    LLAMA_LOG_INFO("%s: prompt eval time = %8.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
+    LLAMA_LOG_INFO("%s: prompt eval time = %10.2f ms / %5d tokens (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_p_eval_ms, timings.n_p_eval, timings.t_p_eval_ms / timings.n_p_eval, 1e3 / timings.t_p_eval_ms * timings.n_p_eval);
-    LLAMA_LOG_INFO("%s:        eval time = %8.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
+    LLAMA_LOG_INFO("%s:        eval time = %10.2f ms / %5d runs   (%8.2f ms per token, %8.2f tokens per second)\n",
             __func__, timings.t_eval_ms, timings.n_eval, timings.t_eval_ms / timings.n_eval, 1e3 / timings.t_eval_ms * timings.n_eval);
-    LLAMA_LOG_INFO("%s:       total time = %8.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms));
+    LLAMA_LOG_INFO("%s:       total time = %10.2f ms\n", __func__, (timings.t_end_ms - timings.t_start_ms));
 }
 
 void llama_reset_timings(struct llama_context * ctx) {

prompts/parallel-questions.txt

@@ -0,0 +1,32 @@
+What do you know about Hobbits?
+What is quantum field theory?
+Why did the chicken cross the road?
+Who is the president of the United States?
+How do I run CMake on MacOS?
+Do you agree that C++ is a really finicky language compared with Python3?
+Is it a good idea to invest in technology?
+Do you like Wagner's Ring?
+Do you think this file input option is really neat?
+What should we all do about climate change?
+Is time-travel possible within the laws of current physics?
+Is it like anything to be a bat?
+Once the chicken has crossed the road, does it try to go back?
+Who is the greatest of all musical composers?
+What is art?
+Is there life elsewhere in the universe?
+What is intelligence?
+What is the difference between knowledge and intelligence?
+Will religion ever die?
+Do we understand ourselves?
+What is the best way to cook eggs?
+If you cannot see things, on what basis do you evaluate them?
+Explain the role of the np junction in photovoltaic cells?
+Is professional sport a good or bad influence on human behaviour?
+Is capital punishment immoral?
+Should we care about other people?
+Who are you?
+Which sense would you surrender if you could?
+Was Henry Ford a hero or a villain?
+Do we need leaders?
+What is nucleosynthesis?
+Who is the greatest scientist of all time so far?