CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-12 10:47:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into compilade/refactor-kv-cache

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-08 17:30:49 -04:00
parent fee3c1d740 d4d915d351
commit 6840ac0bca
242 changed files with 83873 additions and 22119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
llama.h
View File

@@ -97,7 +97,7 @@ extern "C" {
LLAMA_ROPE_TYPE_GLM = 4,
};
enum llama_token_type {
enum llama_token_type { //TODO: remove, required until per token attributes are available from GGUF file
LLAMA_TOKEN_TYPE_UNDEFINED = 0,
LLAMA_TOKEN_TYPE_NORMAL = 1,
LLAMA_TOKEN_TYPE_UNKNOWN = 2,
@@ -107,6 +107,20 @@ extern "C" {
LLAMA_TOKEN_TYPE_BYTE = 6,
};
enum llama_token_attr {
LLAMA_TOKEN_ATTR_UNDEFINED = 0,
LLAMA_TOKEN_ATTR_UNKNOWN = 1 << 0,
LLAMA_TOKEN_ATTR_UNUSED = 1 << 1,
LLAMA_TOKEN_ATTR_NORMAL = 1 << 2,
LLAMA_TOKEN_ATTR_CONTROL = 1 << 3, // SPECIAL?
LLAMA_TOKEN_ATTR_USER_DEFINED = 1 << 4,
LLAMA_TOKEN_ATTR_BYTE = 1 << 5,
LLAMA_TOKEN_ATTR_NORMALIZED = 1 << 6,
LLAMA_TOKEN_ATTR_LSTRIP = 1 << 7,
LLAMA_TOKEN_ATTR_RSTRIP = 1 << 8,
LLAMA_TOKEN_ATTR_SINGLE_WORD = 1 << 9,
};
// model file types
enum llama_ftype {
LLAMA_FTYPE_ALL_F32 = 0,
@@ -351,6 +365,9 @@ extern "C" {
// modifies a preceding LLAMA_GRETYPE_CHAR or
// LLAMA_GRETYPE_CHAR_RNG_UPPER to add an alternate char to match ([ab], [a-zA])
LLAMA_GRETYPE_CHAR_ALT = 6,
// any character (.)
LLAMA_GRETYPE_CHAR_ANY = 7,
};
typedef struct llama_grammar_element {
@@ -871,7 +888,7 @@ extern "C" {
LLAMA_API float llama_token_get_score(const struct llama_model * model, llama_token token);
LLAMA_API enum llama_token_type llama_token_get_type(const struct llama_model * model, llama_token token);
LLAMA_API enum llama_token_attr llama_token_get_attr(const struct llama_model * model, llama_token token);
// Check if the token is supposed to end generation (end-of-generation, eg. EOS, EOT, etc.)
LLAMA_API bool llama_token_is_eog(const struct llama_model * model, llama_token token);
@@ -1092,49 +1109,9 @@ extern "C" {
llama_token token);
//
// Beam search
// Model split
//
struct llama_beam_view {
const llama_token * tokens;
size_t n_tokens;
float p; // Cumulative beam probability (renormalized relative to all beams)
bool eob; // Callback should set this to true when a beam is at end-of-beam.
};
// Passed to beam_search_callback function.
// Whenever 0 < common_prefix_length, this number of tokens should be copied from any of the beams
// (e.g. beams[0]) as they will be removed (shifted) from all beams in all subsequent callbacks.
// These pointers are valid only during the synchronous callback, so should not be saved.
struct llama_beams_state {
struct llama_beam_view * beam_views;
size_t n_beams; // Number of elements in beam_views[].
size_t common_prefix_length; // Current max length of prefix tokens shared by all beams.
bool last_call; // True iff this is the last callback invocation.
};
// Type of pointer to the beam_search_callback function.
// void* callback_data is any custom data passed to llama_beam_search, that is subsequently
// passed back to beam_search_callback. This avoids having to use global variables in the callback.
typedef void (*llama_beam_search_callback_fn_t)(void * callback_data, struct llama_beams_state);
/// @details Deterministically returns entire sentence constructed by a beam search.
/// @param ctx Pointer to the llama_context.
/// @param callback Invoked for each iteration of the beam_search loop, passing in beams_state.
/// @param callback_data A pointer that is simply passed back to callback.
/// @param n_beams Number of beams to use.
/// @param n_past Number of tokens already evaluated.
/// @param n_predict Maximum number of tokens to predict. EOS may occur earlier.
LLAMA_API void llama_beam_search(
struct llama_context * ctx,
llama_beam_search_callback_fn_t callback,
void * callback_data,
size_t n_beams,
int32_t n_past,
int32_t n_predict);
/// @details Build a split GGUF final path for this chunk.
/// llama_split_path(split_path, sizeof(split_path), "/models/ggml-model-q4_0", 2, 4) => split_path = "/models/ggml-model-q4_0-00002-of-00004.gguf"
// Returns the split_path length.