extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-10 02:30:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2025-07-01 12:21:09 +03:00
parent c4ea72be9a
commit 1f816de7da
24 changed files with 1456 additions and 430 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/talk-llama/llama.h
View File

@ -390,6 +390,7 @@ extern "C" {
void * imatrix; // pointer to importance matrix data
void * kv_overrides; // pointer to vector containing overrides
void * tensor_types; // pointer to vector containing tensor types
void * prune_layers; // pointer to vector containing layer indices to prune
} llama_model_quantize_params;
typedef struct llama_logit_bias {
@ -943,12 +944,14 @@ extern "C" {
// Requires the context to have a memory.
// For encode-decoder contexts, processes the batch using the decoder.
// Positive return values does not mean a fatal error, but rather a warning.
// Upon non-zero return values, the memory state is restored to the state before this call
// Upon fatal-error or abort, the ubatches that managed to be been processed will remain in the memory state of the context
// To handle this correctly, query the memory state using llama_memory_seq_pos_min() and llama_memory_seq_pos_max()
// Upon other return values, the memory state is restored to the state before this call
// 0 - success
// 1 - could not find a KV slot for the batch (try reducing the size of the batch or increase the context)
// 2 - aborted
// 2 - aborted (processed ubatches will remain in the context's memory)
// -1 - invalid input batch
// < -1 - error
// < -1 - fatal error (processed ubatches will remain in the context's memory)
LLAMA_API int32_t llama_decode(
struct llama_context * ctx,
struct llama_batch batch);