Files
llama.cpp/src/llama-ext.h
Ruixiang Wang 88a39274ec spec: add EAGLE3 speculative decoding support (#18039)
* llama : enable layer input extraction

* spec: support eagle3

* eagle3: fix params bug

* eagle3: support Gemma4 eagle3 from RedHatAI

* eagle3: set sync when get features from target

Co-authored-by: tnhnyzc <115956684+tnhnyzc@users.noreply.github.com>

* eagle3 : fix ubatch handling in embd_layer_inp extraction and encoder

Co-authored-by: Doğaç Eldenk <dogacel@gmail.com>

* eagle3: adapt to upstream changes

* eagle3: fix rebase issues and adapt to upstream changes

* eagle3:exclude the eagle3 arch from test-llama-archs

* eagle3: fix editorconfig check failures

* eagle3: fix multi-seq issue in d2t vocab mapping

* cont : minor style / clean-up

* spec : remove `common_speculative_setup_draft_model()`

* llama : clean-up unused API

* eagle3: set d2t vocab mapping in decode graph

* cont : assert layer inputs are configured

* hparams : use n_embd_inp instead of n_embd_target_features

* eagle3: make output.weight optional and inherit from target model when needed

* haparams : generic norm-before-residual param

* llama-ext : consistent names

* cont : fix

* hparams : remove target_hidden_size

* cparams : rename output_layer_inp -> embeddings_layer_inp

* arch : reuse ATTN_NORM_2 instead of adding new hidden norm

* llama : clean-up names

* cont : add assert + comment

* Update conversion/llama.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: tnhnyzc <115956684+tnhnyzc@users.noreply.github.com>
Co-authored-by: Doğaç Eldenk <dogacel@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-06-12 10:21:06 +03:00

121 lines
4.3 KiB
C++

#pragma once
// this is a staging header for new llama.cpp API
// breaking changes and C++ are allowed. everything here should be considered WIP
#include "llama.h"
#include <cstdint>
#include <map>
// 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);
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);
//
// device memory querying
//
// "memory" as in physical memory for a buffer type, in bytes
struct llama_memory_breakdown_data {
size_t model = 0; // memory allocated for the model
size_t context = 0; // memory allocated for the context
size_t compute = 0; // memory allocated for temporary compute buffers
size_t total() const {
return model + context + compute;
}
};
struct llama_device_memory_data {
int64_t total;
int64_t free;
llama_memory_breakdown_data mb;
};
// TODO: convert to C-style data structure
using llama_memory_breakdown = std::map<ggml_backend_buffer_type_t, llama_memory_breakdown_data>;
LLAMA_API int32_t llama_model_n_expert (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_devices(const struct llama_model * model);
LLAMA_API ggml_backend_dev_t llama_model_get_device(const struct llama_model * model, int i);
LLAMA_API llama_memory_breakdown llama_get_memory_breakdown(const struct llama_context * ctx);
// Set whether the context outputs nextn embeddings or not
// If masked == true, output the embeddings only for the tokens with batch.logits != 0
// If masked == false, output the embeddings for all tokens in the batch regardless of batch.logits
LLAMA_API void llama_set_embeddings_nextn(struct llama_context * ctx, bool value, bool masked);
// mirrors:
// LLAMA_API float * llama_get_embeddings(struct llama_context * ctx);
LLAMA_API float * llama_get_embeddings_nextn(struct llama_context * ctx);
// LLAMA_API float * llama_get_embeddings_ith(struct llama_context * ctx, int32_t i);
LLAMA_API float * llama_get_embeddings_nextn_ith(struct llama_context * ctx, int32_t i);
// Set whether the context outputs the input embeddings of a specific layer
LLAMA_API void llama_set_embeddings_layer_inp(struct llama_context * ctx, uint32_t lid, bool value);
// mirrors:
// LLAMA_API float * llama_get_embeddings(struct llama_context * ctx);
LLAMA_API float * llama_get_embeddings_layer_inp(struct llama_context * ctx, uint32_t lid);
LLAMA_API llama_context * llama_get_ctx_other(struct llama_context * ctx);
//
// model/context data extraction
//
// returns pointer to the target-model layer indices
LLAMA_API const int32_t * llama_model_target_layer_ids (const struct llama_model * model);
// returns the number of extracted layers from target model
LLAMA_API uint32_t llama_model_target_layer_ids_n(const struct llama_model * model);