vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge and update

Browse source
This commit is contained in:
Henri Vasserman 2023-08-09 00:36:11 +03:00
commit 28046d1e52
No known key found for this signature in database
GPG key ID: 2995FC0F58B1A986
37 changed files with 6347 additions and 2237 deletions
Download patch file Download diff file Expand all files Collapse all files

20
examples/server/server.cpp
View file

@ -613,6 +613,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
fprintf(stdout, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads);
fprintf(stdout, " -c N, --ctx-size N size of the prompt context (default: %d)\n", params.n_ctx);
fprintf(stdout, " -gqa N, --gqa N grouped-query attention factor (TEMP!!! use 8 for LLaMAv2 70B) (default: %d)\n", params.n_gqa);
fprintf(stdout, " -eps N, --rms-norm-eps N rms norm eps (TEMP!!! use 1e-5 for LLaMAv2) (default: %.1e)\n", params.rms_norm_eps);
fprintf(stdout, " --rope-freq-base N RoPE base frequency (default: %.1f)\n", params.rope_freq_base);
fprintf(stdout, " --rope-freq-scale N RoPE frequency scaling factor (default: %g)\n", params.rope_freq_scale);
fprintf(stdout, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
@ -632,6 +633,9 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
fprintf(stdout, " how to split tensors across multiple GPUs, comma-separated list of proportions, e.g. 3,1\n");
fprintf(stdout, " -mg i, --main-gpu i the GPU to use for scratch and small tensors\n");
fprintf(stdout, " -lv, --low-vram don't allocate VRAM scratch buffer\n");
fprintf(stdout, " -mmq, --mul-mat-q use experimental mul_mat_q CUDA kernels instead of cuBLAS. TEMP!!!\n" );
fprintf(stdout, " Reduces VRAM usage by 700/970/1430 MiB for 7b/13b/33b but prompt processing speed\n" );
fprintf(stdout, " is still suboptimal, especially q2_K, q3_K, q5_K, and q6_K.\n" );
#endif
fprintf(stdout, " -m FNAME, --model FNAME\n");
fprintf(stdout, " model path (default: %s)\n", params.model.c_str());
@ -708,6 +712,12 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
break;
}
params.n_gqa = std::stoi(argv[i]);
} else if (arg == "-eps" || arg == "--rms-norm-eps") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.rms_norm_eps = std::stof(argv[i]);
} else if (arg == "--rope-freq-base") {
if (++i >= argc) {
invalid_param = true;
@ -769,13 +779,19 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
}
}
#else
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.", {});
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n", {});
#endif // GGML_USE_CUBLAS
} else if (arg == "--low-vram" || arg == "-lv") {
#ifdef GGML_USE_CUBLAS
params.low_vram = true;
#else
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set lower vram usage.\n");
LOG_WARNING("warning: llama.cpp was compiled without cuBLAS. It is not possible to set lower vram usage.\n", {});
#endif // GGML_USE_CUBLAS
} else if (arg == "--mul-mat-q" || arg == "-mmq") {
#ifdef GGML_USE_CUBLAS
params.mul_mat_q = true;
#else
LOG_WARNING("warning: llama.cpp was compiled without cuBLAS. It is not possible to use mul_mat_q kernels.\n", {});
#endif // GGML_USE_CUBLAS
} else if (arg == "--main-gpu" || arg == "-mg") {
if (++i >= argc) {