Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-09 14:29:06 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into pr/18039

Browse Source
This commit is contained in:
Georgi Gerganov
2026-03-16 15:41:24 +02:00
parent 07e2c9707c 67a2209fab
commit 5bb2d50c0f
857 changed files with 80689 additions and 43153 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+20 -7
View File
@@ -5,6 +5,7 @@
#include "ggml-cpu.h"
#include "ggml-backend.h"
#include "ggml-opt.h"
#include "gguf.h"
#include <stddef.h>
#include <stdint.h>
@@ -152,6 +153,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_TQ1_0 = 36, // except 1d tensors
LLAMA_FTYPE_MOSTLY_TQ2_0 = 37, // except 1d tensors
LLAMA_FTYPE_MOSTLY_MXFP4_MOE = 38, // except 1d tensors
LLAMA_FTYPE_MOSTLY_NVFP4 = 39, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};
@@ -444,19 +446,30 @@ extern "C" {
LLAMA_API void llama_detach_threadpool(struct llama_context * ctx);
typedef void (*llama_model_set_tensor_data_t)(struct ggml_tensor * tensor, void * userdata);
// Create a new model from GGUF metadata as well as a function to set the tensor data
// - tensors are created as GGML_TYPE_F32 by default,
// override by adding a tensor with the same name but a different name to the context
LLAMA_API struct llama_model * llama_model_init_from_user(
struct gguf_context * metadata,
llama_model_set_tensor_data_t set_tensor_data, // function to initialize tensor data with
void * set_tensor_data_ud, // userdata for function
struct llama_model_params params);
DEPRECATED(LLAMA_API struct llama_model * llama_load_model_from_file(
const char * path_model,
struct llama_model_params params),
"use llama_model_load_from_file instead");
// Load the model from a file
// Load a model from a file
// If the file is split into multiple parts, the file name must follow this pattern: <name>-%05d-of-%05d.gguf
// If the split file name does not follow this pattern, use llama_model_load_from_splits
LLAMA_API struct llama_model * llama_model_load_from_file(
const char * path_model,
struct llama_model_params params);
// Load the model from multiple splits (support custom naming scheme)
// Load a model from multiple splits (support custom naming scheme)
// The paths must be in the correct order
LLAMA_API struct llama_model * llama_model_load_from_splits(
const char ** paths,
@@ -1002,7 +1015,7 @@ extern "C" {
// Logits for the ith token. For positive indices, Equivalent to:
// llama_get_logits(ctx) + ctx->output_ids[i]*n_vocab
// Negative indicies can be used to access logits in reverse order, -1 is the last logit.
// Negative indices can be used to access logits in reverse order, -1 is the last logit.
// returns NULL for invalid ids.
LLAMA_API float * llama_get_logits_ith(struct llama_context * ctx, int32_t i);
@@ -1017,7 +1030,7 @@ extern "C" {
// Get the embeddings for the ith token. For positive indices, Equivalent to:
// llama_get_embeddings(ctx) + ctx->output_ids[i]*n_embd
// Negative indicies can be used to access embeddings in reverse order, -1 is the last embedding.
// Negative indices can be used to access embeddings in reverse order, -1 is the last embedding.
// shape: [n_embd] (1-dimensional)
// returns NULL for invalid ids.
LLAMA_API float * llama_get_embeddings_ith(struct llama_context * ctx, int32_t i);
@@ -1037,9 +1050,9 @@ extern "C" {
// Returns LLAMA_TOKEN_NULL if no token was sampled.
LLAMA_API llama_token llama_get_sampled_token_ith(struct llama_context * ctx, int32_t i);
// Get the backend sampled probabilites for the ith token
// Get the backend sampled probabilities for the ith token
// The index matches llama_get_sampled_token_ith().
// Returns NULL if no probabilites were generated.
// Returns NULL if no probabilities were generated.
LLAMA_API float * llama_get_sampled_probs_ith (struct llama_context * ctx, int32_t i);
LLAMA_API uint32_t llama_get_sampled_probs_count_ith(struct llama_context * ctx, int32_t i);
@@ -1366,7 +1379,7 @@ extern "C" {
float tau,
float eta);
/// @details Intializes a GBNF grammar, see grammars/README.md for details.
/// @details Initializes a GBNF grammar, see grammars/README.md for details.
/// @param vocab The vocabulary that this grammar will be used with.
/// @param grammar_str The production rules for the grammar, encoded as a string. Returns an empty grammar if empty. Returns NULL if parsing of grammar_str fails.
/// @param grammar_root The name of the start symbol for the grammar.