Remove unused n_parts parameter (ggml-org#1509)

Author: sw

examples/common.cpp

@@ -321,12 +321,6 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 invalid_param = true;
                 break;
             }
-        } else if (arg == "--n-parts") {
-            if (++i >= argc) {
-                invalid_param = true;
-                break;
-            }
-            params.n_parts = std::stoi(argv[i]);
         } else if (arg == "-h" || arg == "--help") {
             gpt_print_usage(argc, argv, default_params);
             exit(0);
@@ -418,7 +412,6 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stderr, "  --no-penalize-nl      do not penalize newline token\n");
     fprintf(stderr, "  --memory-f32          use f32 instead of f16 for memory key+value\n");
     fprintf(stderr, "  --temp N              temperature (default: %.1f)\n", (double)params.temp);
-    fprintf(stderr, "  --n-parts N           number of model parts (default: -1 = determine from dimensions)\n");
     fprintf(stderr, "  -b N, --batch-size N  batch size for prompt processing (default: %d)\n", params.n_batch);
     fprintf(stderr, "  --perplexity          compute perplexity over the prompt\n");
     fprintf(stderr, "  --keep                number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
@@ -473,7 +466,6 @@ struct llama_context * llama_init_from_gpt_params(const gpt_params & params) {
     auto lparams = llama_context_default_params();
 
     lparams.n_ctx        = params.n_ctx;
-    lparams.n_parts      = params.n_parts;
     lparams.n_gpu_layers = params.n_gpu_layers;
     lparams.seed         = params.seed;
     lparams.f16_kv       = params.memory_f16;

examples/common.h

@@ -24,7 +24,6 @@ struct gpt_params {
     int32_t seed          = -1;  // RNG seed
     int32_t n_threads     = get_num_physical_cores();
     int32_t n_predict     = -1;  // new tokens to predict
-    int32_t n_parts       = -1;  // amount of model parts (-1 = determine from model dimensions)
     int32_t n_ctx         = 512; // context size
     int32_t n_batch       = 512; // batch size for prompt processing (must be >=32 to use BLAS)
     int32_t n_keep        = 0;   // number of tokens to keep from initial prompt

examples/quantize-stats/quantize-stats.cpp

@@ -321,7 +321,6 @@ int main(int argc, char ** argv) {
         auto lparams = llama_context_default_params();
 
         lparams.n_ctx      = 256;
-        lparams.n_parts    = 1;
         lparams.seed       = 1;
         lparams.f16_kv     = false;
         lparams.use_mlock  = false;

examples/save-load-state/save-load-state.cpp

@@ -26,7 +26,6 @@ int main(int argc, char ** argv) {
     auto lparams = llama_context_default_params();
 
     lparams.n_ctx     = params.n_ctx;
-    lparams.n_parts   = params.n_parts;
     lparams.seed      = params.seed;
     lparams.f16_kv    = params.memory_f16;
     lparams.use_mmap  = params.use_mmap;

llama.cpp

@@ -820,7 +820,6 @@ static bool kv_cache_init(
 struct llama_context_params llama_context_default_params() {
     struct llama_context_params result = {
         /*.n_ctx                       =*/ 512,
-        /*.n_parts                     =*/ -1,
         /*.gpu_layers                  =*/ 0,
         /*.seed                        =*/ -1,
         /*.f16_kv                      =*/ false,

llama.h

@@ -55,7 +55,6 @@ extern "C" {
 
     struct llama_context_params {
         int n_ctx;        // text context
-        int n_parts;      // -1 for default
         int n_gpu_layers; // number of layers to store in VRAM
         int seed;         // RNG seed, -1 for random