Merge branch 'master' into speculative-tree

examples/finetune/finetune.cpp

@@ -529,13 +529,14 @@ static void init_lora(const struct my_llama_model * model, struct my_llama_lora
     set_param_lora(lora);
 
     // measure data size
-    struct ggml_allocr * alloc = NULL;
-    alloc = ggml_allocr_new_measure(tensor_alignment);
-    alloc_lora(alloc, lora);
+    size_t size = 0;
+    for (struct ggml_tensor * t = ggml_get_first_tensor(ctx); t != NULL; t = ggml_get_next_tensor(ctx, t)) {
+        size += GGML_PAD(ggml_nbytes(t), tensor_alignment);
+    }
 
     // allocate data
-    lora->data.resize(ggml_allocr_max_size(alloc) + tensor_alignment);
-    ggml_allocr_free(alloc);
+    struct ggml_allocr * alloc = NULL;
+    lora->data.resize(size + tensor_alignment);
     alloc = ggml_allocr_new(lora->data.data(), lora->data.size(), tensor_alignment);
     alloc_lora(alloc, lora);
     ggml_allocr_free(alloc);
@@ -1714,11 +1715,9 @@ int main(int argc, char ** argv) {
     struct ggml_tensor * target_probs  = ggml_new_tensor_3d(ctx_input, GGML_TYPE_F32, n_vocab,  n_tokens, n_batch);
 
     // measure required memory for input tensors
-    alloc = ggml_allocr_new_measure(tensor_alignment);
-    ggml_allocr_alloc(alloc, tokens_input);
-    ggml_allocr_alloc(alloc, target_probs);
-    size_t max_input_size = ggml_allocr_max_size(alloc) + tensor_alignment;
-    ggml_allocr_free(alloc);
+    size_t max_input_size = GGML_PAD(ggml_nbytes(tokens_input), tensor_alignment) +
+                            GGML_PAD(ggml_nbytes(target_probs), tensor_alignment) +
+                            tensor_alignment;
     printf("%s: input_size = %zu bytes (%.1f MB)\n", __func__, max_input_size, (float) max_input_size / (1024.0f*1024.0f));
 
     // allocate input tensors

examples/llava/llava-utils.h

@@ -49,9 +49,9 @@ inline bool eval_id(struct llama_context * ctx_llama, int id, int * n_past) {
     return eval_tokens(ctx_llama, tokens, 1, n_past);
 }
 
-inline bool eval_string(struct llama_context * ctx_llama, const char* str, int n_batch, int * n_past){
+inline bool eval_string(struct llama_context * ctx_llama, const char* str, int n_batch, int * n_past, bool add_bos){
     std::string              str2     = str;
-    std::vector<llama_token> embd_inp = ::llama_tokenize(ctx_llama, str2, true);
+    std::vector<llama_token> embd_inp = ::llama_tokenize(ctx_llama, str2, add_bos);
     eval_tokens(ctx_llama, embd_inp, n_batch, n_past);
     return true;
 }

examples/llava/llava.cpp

@@ -79,7 +79,13 @@ int main(int argc, char ** argv) {
 
     llama_backend_init(params.numa);
 
-    llama_model_params model_params = llama_model_default_params();
+    llama_model_params model_params              = llama_model_default_params();
+                       model_params.n_gpu_layers = params.n_gpu_layers;
+                       model_params.main_gpu     = params.main_gpu;
+                       model_params.tensor_split = params.tensor_split;
+                       model_params.use_mmap     = params.use_mmap;
+                       model_params.use_mlock    = params.use_mlock;
+
     llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
     if (model == NULL) {
         fprintf(stderr , "%s: error: unable to load model\n" , __func__);
@@ -91,6 +97,7 @@ int main(int argc, char ** argv) {
     ctx_params.n_ctx           = params.n_ctx < 2048 ? 2048 : params.n_ctx; // we need a longer context size to process image embeddings
     ctx_params.n_threads       = params.n_threads;
     ctx_params.n_threads_batch = params.n_threads_batch == -1 ? params.n_threads : params.n_threads_batch;
+    ctx_params.seed            = params.seed;
 
     llama_context * ctx_llama = llama_new_context_with_model(model, ctx_params);
 
@@ -100,7 +107,8 @@ int main(int argc, char ** argv) {
     }
 
     // make sure that the correct mmproj was used, i.e., compare apples to apples
-    int n_llama_embd = llama_n_embd(llama_get_model(ctx_llama));
+    const int n_llama_embd = llama_n_embd(llama_get_model(ctx_llama));
+
     if (n_img_embd != n_llama_embd) {
         printf("%s: embedding dim of the multimodal projector (%d) is not equal to that of LLaMA (%d). Make sure that you use the correct mmproj file.\n", __func__, n_img_embd, n_llama_embd);
 
@@ -119,14 +127,14 @@ int main(int argc, char ** argv) {
 
     const int max_tgt_len = params.n_predict < 0 ? 256 : params.n_predict;
 
-    // GG: are we sure that there should be a trailing whitespace at the end of this string?
-    eval_string(ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER: ", params.n_batch, &n_past);
+    eval_string(ctx_llama, "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\nUSER:", params.n_batch, &n_past, true);
     eval_image_embd(ctx_llama, image_embd, n_img_pos, params.n_batch, &n_past);
-    eval_string(ctx_llama, params.prompt.c_str(), params.n_batch, &n_past);
-    eval_string(ctx_llama, "\nASSISTANT:",        params.n_batch, &n_past);
+    eval_string(ctx_llama, (params.prompt + "\nASSISTANT:").c_str(), params.n_batch, &n_past, false);
 
     // generate the response
 
+    printf("\n");
+    printf("prompt: '%s'\n", params.prompt.c_str());
     printf("\n");
 
     for (int i = 0; i < max_tgt_len; i++) {