ExternalVendorCode/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-17 06:18:08 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-10 10:12:44 +03:00
parent 96eaf46ec6
commit db264d6220
23 changed files with 911 additions and 437 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
examples/talk-llama/llama-context.h
View File

@ -13,13 +13,12 @@
#include <vector>
struct llama_model;
struct llama_kv_cache;
class llama_io_read_i;
class llama_io_write_i;
class llama_memory_i;
class llama_memory_state_i;
struct llama_memory_i;
struct llama_memory_state_i;
struct llama_context {
// init scheduler and compute buffers, reserve worst-case graphs
@ -47,12 +46,12 @@ struct llama_context {
uint32_t n_threads() const;
uint32_t n_threads_batch() const;
llama_kv_cache * get_kv_self();
const llama_kv_cache * get_kv_self() const;
llama_memory_t get_memory() const;
// return true of the KV cache was updated
// TODO: remove
bool kv_self_update();
bool kv_self_update(bool optimize);
void kv_self_defrag_sched();
enum llama_pooling_type pooling_type() const;
@ -231,6 +230,9 @@ private:
std::unique_ptr<llama_memory_i> memory;
// TODO: temporary, until the llama_kv_self_defrag() API is removed
bool memory_force_optimize = false;
// decode output (2-dimensional array: [n_outputs][n_vocab])
size_t logits_size = 0; // capacity (of floats) for logits
float * logits = nullptr;