extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-09 15:16:08 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-18 10:22:47 +03:00
parent 69061e356f
commit 2f60ebc3c2
26 changed files with 1454 additions and 504 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
examples/talk-llama/llama.h
View File

@ -243,18 +243,21 @@ extern "C" {
typedef bool (*llama_progress_callback)(float progress, void * user_data);
// Input data for llama_decode
// Input data for llama_encode/llama_decode
// A llama_batch object can contain input about one or many sequences
// The provided arrays (i.e. token, embd, pos, etc.) must have size of n_tokens
//
// - token : the token ids of the input (used when embd is NULL)
// - embd : token embeddings (i.e. float vector of size n_embd) (used when token is NULL)
// - pos : the positions of the respective token in the sequence
// (if set to NULL, the token position will be tracked automatically by llama_decode)
// (if set to NULL, the token position will be tracked automatically by llama_encode/llama_decode)
// - seq_id : the sequence to which the respective token belongs
// (if set to NULL, the sequence ID will be assumed to be 0)
// - logits : if zero, the logits (and/or the embeddings) for the respective token will not be output
// (if set to NULL, only the logits for last token will be returned)
// (if set to NULL:
// - if embeddings: all tokens are output
// - if not: only the last token is output
// )
//
typedef struct llama_batch {
int32_t n_tokens;
@ -262,8 +265,8 @@ extern "C" {
llama_token * token;
float * embd;
llama_pos * pos;
int32_t * n_seq_id; // TODO: remove, should belong to only 1 sequence
llama_seq_id ** seq_id; // TODO: become llama_seq_id * seq_id;
int32_t * n_seq_id;
llama_seq_id ** seq_id;
int8_t * logits; // TODO: rename this to "output"
} llama_batch;
@ -961,8 +964,8 @@ extern "C" {
// Get the number of threads used for prompt and batch processing (multiple token).
LLAMA_API int32_t llama_n_threads_batch(struct llama_context * ctx);
// Set whether the model is in embeddings mode or not
// If true, embeddings will be returned but logits will not
// Set whether the context outputs embeddings or not
// TODO: rename to avoid confusion with llama_get_embeddings()
LLAMA_API void llama_set_embeddings(struct llama_context * ctx, bool embeddings);
// Set whether to use causal attention or not