diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 4f46563e2..c383dc027 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -1,14 +1,434 @@ -#include -#include -#include +// Defines sigaction on msys: +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif #include "common.h" #include "llama.h" #include "crow.h" +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) +#include +#include +#elif defined (_WIN32) +#include +#endif + +static console_state con_st; +static llama_context ** g_ctx; + +static bool is_interacting = false; + +#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32) +void sigint_handler(int signo) { + set_console_color(con_st, CONSOLE_COLOR_DEFAULT); + printf("\n"); // this also force flush stdout. + if (signo == SIGINT) { + if (!is_interacting) { + is_interacting=true; + } else { + llama_print_timings(*g_ctx); + _exit(130); + } + } +} +#endif + auto const BINDPORT = 8001; +int run_llama(llama_context * ctx, gpt_params params, std::ostream * outfile) { + if (!params.lora_adapter.empty()) { + int err = llama_apply_lora_from_file(ctx, + params.lora_adapter.c_str(), + params.lora_base.empty() ? NULL : params.lora_base.c_str(), + params.n_threads); + if (err != 0) { + fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__); + return 1; + } + } + + // print system information + { + fprintf(stderr, "\n"); + fprintf(stderr, "system_info: n_threads = %d / %d | %s\n", + params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info()); + } + + // determine the maximum memory usage needed to do inference for the given n_batch and n_predict parameters + // uncomment the "used_mem" line in llama.cpp to see the results + if (params.mem_test) { + { + const std::vector tmp(params.n_batch, 0); + llama_eval(ctx, tmp.data(), tmp.size(), 0, params.n_threads); + } + + { + const std::vector tmp = { 0, }; + llama_eval(ctx, tmp.data(), tmp.size(), params.n_predict - 1, params.n_threads); + } + + llama_print_timings(ctx); + llama_free(ctx); + + return 0; + } + + // Add a space in front of the first character to match OG llama tokenizer behavior + params.prompt.insert(0, 1, ' '); + + // tokenize the prompt + auto embd_inp = ::llama_tokenize(ctx, params.prompt, true); + + const int n_ctx = llama_n_ctx(ctx); + + if ((int) embd_inp.size() > n_ctx - 4) { + fprintf(stderr, "%s: error: prompt is too long (%d tokens, max %d)\n", __func__, (int) embd_inp.size(), n_ctx - 4); + return 1; + } + + // number of tokens to keep when resetting context + if (params.n_keep < 0 || params.n_keep > (int)embd_inp.size() || params.instruct) { + params.n_keep = (int)embd_inp.size(); + } + + // prefix & suffix for instruct mode + const auto inp_pfx = ::llama_tokenize(ctx, "\n\n### Instruction:\n\n", true); + const auto inp_sfx = ::llama_tokenize(ctx, "\n\n### Response:\n\n", false); + + // in instruct mode, we inject a prefix and a suffix to each input by the user + if (params.instruct) { + params.interactive_first = true; + params.antiprompt.push_back("### Instruction:\n\n"); + } + + // enable interactive mode if reverse prompt or interactive start is specified + if (params.antiprompt.size() != 0 || params.interactive_first) { + params.interactive = true; + } + + // determine newline token + auto llama_token_newline = ::llama_tokenize(ctx, "\n", false); + + if (params.verbose_prompt) { + fprintf(stderr, "\n"); + fprintf(stderr, "%s: prompt: '%s'\n", __func__, params.prompt.c_str()); + fprintf(stderr, "%s: number of tokens in prompt = %zu\n", __func__, embd_inp.size()); + for (int i = 0; i < (int) embd_inp.size(); i++) { + fprintf(stderr, "%6d -> '%s'\n", embd_inp[i], llama_token_to_str(ctx, embd_inp[i])); + } + if (params.n_keep > 0) { + fprintf(stderr, "%s: static prompt based on n_keep: '", __func__); + for (int i = 0; i < params.n_keep; i++) { + fprintf(stderr, "%s", llama_token_to_str(ctx, embd_inp[i])); + } + fprintf(stderr, "'\n"); + } + fprintf(stderr, "\n"); + } + + if (params.interactive) { +#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) + struct sigaction sigint_action; + sigint_action.sa_handler = sigint_handler; + sigemptyset (&sigint_action.sa_mask); + sigint_action.sa_flags = 0; + sigaction(SIGINT, &sigint_action, NULL); +#elif defined (_WIN32) + signal(SIGINT, sigint_handler); +#endif + + fprintf(stderr, "%s: interactive mode on.\n", __func__); + + if (params.antiprompt.size()) { + for (auto antiprompt : params.antiprompt) { + fprintf(stderr, "Reverse prompt: '%s'\n", antiprompt.c_str()); + } + } + + if (!params.input_prefix.empty()) { + fprintf(stderr, "Input prefix: '%s'\n", params.input_prefix.c_str()); + } + } + fprintf(stderr, "sampling: temp = %f, top_k = %d, top_p = %f, repeat_last_n = %i, repeat_penalty = %f\n", + params.temp, params.top_k, params.top_p, params.repeat_last_n, params.repeat_penalty); + fprintf(stderr, "generate: n_ctx = %d, n_batch = %d, n_predict = %d, n_keep = %d\n", n_ctx, params.n_batch, params.n_predict, params.n_keep); + fprintf(stderr, "\n\n"); + + // TODO: replace with ring-buffer + std::vector last_n_tokens(n_ctx); + std::fill(last_n_tokens.begin(), last_n_tokens.end(), 0); + + if (params.interactive) { + fprintf(stderr, "== Running in interactive mode. ==\n" +#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32) + " - Press Ctrl+C to interject at any time.\n" +#endif + " - Press Return to return control to LLaMa.\n" + " - If you want to submit another line, end your input in '\\'.\n\n"); + is_interacting = params.interactive_first; + } + + bool is_antiprompt = false; + bool input_noecho = false; + + int n_past = 0; + int n_remain = params.n_predict; + int n_consumed = 0; + + // the first thing we will do is to output the prompt, so set color accordingly + set_console_color(con_st, CONSOLE_COLOR_PROMPT); + + std::vector embd; + + while (n_remain != 0 || params.interactive) { + // predict + if (embd.size() > 0) { + // infinite text generation via context swapping + // if we run out of context: + // - take the n_keep first tokens from the original prompt (via n_past) + // - take half of the last (n_ctx - n_keep) tokens and recompute the logits in batches + if (n_past + (int) embd.size() > n_ctx) { + const int n_left = n_past - params.n_keep; + + n_past = params.n_keep; + + // insert n_left/2 tokens at the start of embd from last_n_tokens + embd.insert(embd.begin(), last_n_tokens.begin() + n_ctx - n_left/2 - embd.size(), last_n_tokens.end() - embd.size()); + + //printf("\n---\n"); + //printf("resetting: '"); + //for (int i = 0; i < (int) embd.size(); i++) { + // printf("%s", llama_token_to_str(ctx, embd[i])); + //} + //printf("'\n"); + //printf("\n---\n"); + } + + // evaluate tokens in batches + // embd is typically prepared beforehand to fit within a batch, but not always + for (int i = 0; i < (int) embd.size(); i += params.n_batch) { + int n_eval = (int) embd.size() - i; + if (n_eval > params.n_batch) { + n_eval = params.n_batch; + } + if (llama_eval(ctx, &embd[i], n_eval, n_past, params.n_threads)) { + fprintf(stderr, "%s : failed to eval\n", __func__); + return 1; + } + n_past += n_eval; + } + } + + embd.clear(); + + if ((int) embd_inp.size() <= n_consumed && !is_interacting) { + // out of user input, sample next token + const int32_t top_k = params.top_k; + const float top_p = params.top_p; + const float temp = params.temp; + const float repeat_penalty = params.repeat_penalty; + + llama_token id = 0; + + { + auto logits = llama_get_logits(ctx); + + if (params.ignore_eos) { + logits[llama_token_eos()] = 0; + } + + id = llama_sample_top_p_top_k(ctx, + last_n_tokens.data() + n_ctx - params.repeat_last_n, + params.repeat_last_n, top_k, top_p, temp, repeat_penalty); + + last_n_tokens.erase(last_n_tokens.begin()); + last_n_tokens.push_back(id); + } + + // replace end of text token with newline token when in interactive mode + if (id == llama_token_eos() && params.interactive && !params.instruct) { + id = llama_token_newline.front(); + if (params.antiprompt.size() != 0) { + // tokenize and inject first reverse prompt + const auto first_antiprompt = ::llama_tokenize(ctx, params.antiprompt.front(), false); + embd_inp.insert(embd_inp.end(), first_antiprompt.begin(), first_antiprompt.end()); + } + } + + // add it to the context + embd.push_back(id); + + // echo this to console + input_noecho = false; + + // decrement remaining sampling budget + --n_remain; + } else { + // some user input remains from prompt or interaction, forward it to processing + while ((int) embd_inp.size() > n_consumed) { + embd.push_back(embd_inp[n_consumed]); + last_n_tokens.erase(last_n_tokens.begin()); + last_n_tokens.push_back(embd_inp[n_consumed]); + ++n_consumed; + if ((int) embd.size() >= params.n_batch) { + break; + } + } + } + + // display text + if (!input_noecho) { + for (auto id : embd) { + *outfile << llama_token_to_str(ctx, id) << std::flush; + } + } + // reset color to default if we there is no pending user input + if (!input_noecho && (int)embd_inp.size() == n_consumed) { + set_console_color(con_st, CONSOLE_COLOR_DEFAULT); + } + + // in interactive mode, and not currently processing queued inputs; + // check if we should prompt the user for more + if (params.interactive && (int) embd_inp.size() <= n_consumed) { + + // check for reverse prompt + if (params.antiprompt.size()) { + std::string last_output; + for (auto id : last_n_tokens) { + last_output += llama_token_to_str(ctx, id); + } + + is_antiprompt = false; + // Check if each of the reverse prompts appears at the end of the output. + for (std::string & antiprompt : params.antiprompt) { + if (last_output.find(antiprompt.c_str(), last_output.length() - antiprompt.length(), antiprompt.length()) != std::string::npos) { + is_interacting = true; + is_antiprompt = true; + set_console_color(con_st, CONSOLE_COLOR_USER_INPUT); + fflush(stdout); + break; + } + } + } + + if (n_past > 0 && is_interacting) { + // potentially set color to indicate we are taking user input + set_console_color(con_st, CONSOLE_COLOR_USER_INPUT); + +#if defined (_WIN32) + // Windows: must reactivate sigint handler after each signal + signal(SIGINT, sigint_handler); +#endif + + if (params.instruct) { + printf("\n> "); + } + + std::string buffer; + if (!params.input_prefix.empty()) { + buffer += params.input_prefix; + printf("%s", buffer.c_str()); + } + + std::string line; + bool another_line = true; + do { +#if defined(_WIN32) + std::wstring wline; + if (!std::getline(std::wcin, wline)) { + // input stream is bad or EOF received + return 0; + } + win32_utf8_encode(wline, line); +#else + if (!std::getline(std::cin, line)) { + // input stream is bad or EOF received + return 0; + } +#endif + if (line.empty() || line.back() != '\\') { + another_line = false; + } else { + line.pop_back(); // Remove the continue character + } + buffer += line + '\n'; // Append the line to the result + } while (another_line); + + // done taking input, reset color + set_console_color(con_st, CONSOLE_COLOR_DEFAULT); + + // Add tokens to embd only if the input buffer is non-empty + // Entering a empty line lets the user pass control back + if (buffer.length() > 1) { + + // instruct mode: insert instruction prefix + if (params.instruct && !is_antiprompt) { + n_consumed = embd_inp.size(); + embd_inp.insert(embd_inp.end(), inp_pfx.begin(), inp_pfx.end()); + } + + auto line_inp = ::llama_tokenize(ctx, buffer, false); + embd_inp.insert(embd_inp.end(), line_inp.begin(), line_inp.end()); + + // instruct mode: insert response suffix + if (params.instruct) { + embd_inp.insert(embd_inp.end(), inp_sfx.begin(), inp_sfx.end()); + } + + n_remain -= line_inp.size(); + } + + input_noecho = true; // do not echo this again + } + + if (n_past > 0) { + is_interacting = false; + } + } + + // end of text token + if (!embd.empty() && embd.back() == llama_token_eos()) { + if (params.instruct) { + is_interacting = true; + } else { + fprintf(stderr, " [end of text]\n"); + break; + } + } + + // In interactive mode, respect the maximum number of tokens and drop back to user input when reached. + if (params.interactive && n_remain <= 0 && params.n_predict != -1) { + n_remain = params.n_predict; + is_interacting = true; + } + } + +#if defined (_WIN32) + signal(SIGINT, SIG_DFL); +#endif + + llama_print_timings(ctx); + llama_free(ctx); + + set_console_color(con_st, CONSOLE_COLOR_DEFAULT); + + return 0; +} + int main(int argc, char ** argv) { gpt_params params; params.model = "models/llama-7B/ggml-model.bin"; @@ -47,15 +467,6 @@ int main(int argc, char ** argv) { crow::SimpleApp app; // app.loglevel(crow::LogLevel::Warning); - - /// Python server will send a file name to you. - /// You should open that file and give the pointer to run_llama. - /// run_llama will keep writing the output to it. - /// The python server will keep reading from that file just like it reads - /// from the stdout of the main process. - /// - /// We are doing this because this is probably the simplest way - /// to get streaming to work here. CROW_ROUTE(app, "/completion").methods("POST"_method) ([¶ms, &ctx](const crow::request& req){ @@ -76,6 +487,15 @@ int main(int argc, char ** argv) { runparams.repeat_penalty = (float)body["repeat_penalty"].d(); runparams.embedding = false; + /// The client will send a file name to you. + /// You should open that file and give the pointer to run_llama. + /// run_llama will keep writing the output to it. + /// The python server will keep reading from that file just like it reads + /// from the stdout of the main process. + /// + /// We are doing this because this is probably the simplest way + /// to get streaming to work here. + // Open the tempfile into a stream. std::ofstream outfile(body["tempfile"].s(), std::ios::out); @@ -85,26 +505,26 @@ int main(int argc, char ** argv) { return crow::response(crow::status::OK); }); - CROW_ROUTE(app, "/embedding").methods("POST"_method) - ([¶ms, &ctx](const crow::request& req){ - auto body = crow::json::load(req.body); - if (!body) return crow::response(crow::status::BAD_REQUEST); + // CROW_ROUTE(app, "/embedding").methods("POST"_method) + // ([¶ms, &ctx](const crow::request& req){ + // auto body = crow::json::load(req.body); + // if (!body) return crow::response(crow::status::BAD_REQUEST); - // Create new params for this request only - gpt_params runparams = params; + // // Create new params for this request only + // gpt_params runparams = params; - // Set run params from body - runparams.prompt = body["prompt"].s(); - runparams.embedding = true; + // // Set run params from body + // runparams.prompt = body["prompt"].s(); + // runparams.embedding = true; - // Open the tempfile into a stream. - std::ofstream outfile(body["tempfile"].s(), std::ios::out); + // // Open the tempfile into a stream. + // std::ofstream outfile(body["tempfile"].s(), std::ios::out); - // Write output of LLaMA to file stream. - run_llama_embedding(ctx, runparams, &outfile); + // // Write output of LLaMA to file stream. + // run_llama_embedding(ctx, runparams, &outfile); - return crow::response(crow::status::OK); - }); + // return crow::response(crow::status::OK); + // }); app.port(BINDPORT).multithreaded().run(); return 0;