vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : remove beam search (#7736)

Browse source
This commit is contained in:
Georgi Gerganov 2024-06-04 21:23:05 +03:00 • committed by GitHub
parent 5ca0944a15
commit 0cd6bd3483
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 2 additions and 494 deletions
Download patch file Download diff file Expand all files Collapse all files

42
llama.h
View file

@ -1056,49 +1056,9 @@ 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.