ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-05 11:30:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge mainline - Aug 12 2024 (#17)

Browse Source 
* Merge mainline

* Fix after merge

* Remove CI check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-08-12 15:14:32 +02:00
committed by GitHub
parent 5ed6d94cb5
commit 1a4cfbcc53
164 changed files with 9041 additions and 3404 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
include/llama.h
View File

@@ -33,17 +33,15 @@
#define LLAMA_DEFAULT_SEED 0xFFFFFFFF
#define LLAMA_MAX_RNG_STATE (64*1024)
#define LLAMA_FILE_MAGIC_GGLA 0x67676c61u // 'ggla'
#define LLAMA_FILE_MAGIC_GGSN 0x6767736eu // 'ggsn'
#define LLAMA_FILE_MAGIC_GGSQ 0x67677371u // 'ggsq'
#define LLAMA_SESSION_MAGIC LLAMA_FILE_MAGIC_GGSN
#define LLAMA_SESSION_VERSION 7
#define LLAMA_SESSION_VERSION 8
#define LLAMA_STATE_SEQ_MAGIC LLAMA_FILE_MAGIC_GGSQ
#define LLAMA_STATE_SEQ_VERSION 1
#define LLAMA_STATE_SEQ_VERSION 2
#ifdef __cplusplus
extern "C" {
@@ -355,7 +353,7 @@ extern "C" {
int32_t nthread; // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
enum llama_ftype ftype; // quantize to this llama_ftype
enum ggml_type output_tensor_type; // output tensor type
enum ggml_type token_embedding_type; // itoken embeddings tensor type
enum ggml_type token_embedding_type; // token embeddings tensor type
bool allow_requantize; // allow quantizing non-f32/f16 tensors
bool quantize_output_tensor; // quantize output.weight
bool only_copy; // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
@@ -515,6 +513,9 @@ extern "C" {
// Returns true if the model contains an encoder that requires llama_encode() call
LLAMA_API bool llama_model_has_encoder(const struct llama_model * model);
// Returns true if the model contains a decoder that requires llama_decode() call
LLAMA_API bool llama_model_has_decoder(const struct llama_model * model);
// For encoder-decoder models, this function returns id of the token that must be provided
// to the decoder to start generating output sequence. For other models, it returns -1.
LLAMA_API llama_token llama_model_decoder_start_token(const struct llama_model * model);
@@ -700,10 +701,11 @@ extern "C" {
// State / sessions
//
// Returns the maximum size in bytes of the state (rng, logits, embedding
// and kv_cache) - will often be smaller after compacting tokens
LLAMA_API size_t llama_state_get_size(const struct llama_context * ctx);
LLAMA_API DEPRECATED(size_t llama_get_state_size(const struct llama_context * ctx),
// Returns the *actual* size in bytes of the state
// (rng, logits, embedding and kv_cache)
// Only use when saving the state, not when restoring it, otherwise the size may be too small.
LLAMA_API size_t llama_state_get_size(struct llama_context * ctx);
LLAMA_API DEPRECATED(size_t llama_get_state_size(struct llama_context * ctx),
"use llama_state_get_size instead");
// Copies the state to the specified destination address.
@@ -711,7 +713,8 @@ extern "C" {
// Returns the number of bytes copied
LLAMA_API size_t llama_state_get_data(
struct llama_context * ctx,
uint8_t * dst);
uint8_t * dst,
size_t size);
LLAMA_API DEPRECATED(size_t llama_copy_state_data(
struct llama_context * ctx,
uint8_t * dst),
@@ -721,7 +724,8 @@ extern "C" {
// Returns the number of bytes read
LLAMA_API size_t llama_state_set_data(
struct llama_context * ctx,
const uint8_t * src);
const uint8_t * src,
size_t size);
LLAMA_API DEPRECATED(size_t llama_set_state_data(
struct llama_context * ctx,
const uint8_t * src),
@@ -763,6 +767,7 @@ extern "C" {
LLAMA_API size_t llama_state_seq_get_data(
struct llama_context * ctx,
uint8_t * dst,
size_t size,
llama_seq_id seq_id);
// Copy the sequence data (originally copied with `llama_state_seq_get_data`) into the specified sequence
@@ -772,6 +777,7 @@ extern "C" {
LLAMA_API size_t llama_state_seq_set_data(
struct llama_context * ctx,
const uint8_t * src,
size_t size,
llama_seq_id dest_seq_id);
LLAMA_API size_t llama_state_seq_save_file(