llama.cpp/src/llama-ext.h

57 lines
1.8 KiB
C++

#pragma once
#include "llama.h"
#include <cstdint>
// Reserve a new compute graph. It is valid until the next call to llama_graph_reserve.
LLAMA_API struct ggml_cgraph * llama_graph_reserve(
struct llama_context * ctx,
uint32_t n_tokens,
uint32_t n_seqs,
uint32_t n_outputs);
// Get the default ggml_type for a given ftype.
LLAMA_API ggml_type llama_ftype_get_default_type(llama_ftype ftype);
// Quantization state.
struct quantize_state_impl;
LLAMA_API quantize_state_impl * llama_quant_init(
const llama_model * model,
const llama_model_quantize_params * params);
LLAMA_API void llama_quant_free(quantize_state_impl * qs);
// Descriptor for constructing a mock model for quantization testing.
struct llama_quant_model_desc {
const char * architecture;
uint32_t n_embd;
uint32_t n_ff;
uint32_t n_layer;
uint32_t n_head;
uint32_t n_head_kv;
uint32_t n_expert;
uint32_t n_embd_head_k;
uint32_t n_embd_head_v;
};
// Create a mock model from a metadata descriptor (for testing).
// The returned model must be freed with llama_model_free().
LLAMA_API llama_model * llama_quant_model_from_metadata(const llama_quant_model_desc * desc);
// Returns true if this tensor should be quantized (based on name, dims, params).
LLAMA_API bool llama_quant_tensor_allows_quantization(
const quantize_state_impl * qs,
const ggml_tensor * tensor);
// Compute quantization type assignments for a list of tensors.
// All tensors should be quantizable (use llama_quant_tensor_allows_quantization to filter).
// result_types: caller-allocated array of n_tensors elements, filled with assigned types.
LLAMA_API void llama_quant_compute_types(
quantize_state_impl * qs,
llama_ftype ftype,
ggml_tensor ** tensors,
ggml_type * result_types,
size_t n_tensors);