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

32
examples/talk-llama/llama-kv-cache-recurrent.h
View File

@ -2,7 +2,7 @@
#include "llama-batch.h"
#include "llama-graph.h"
#include "llama-kv-cache.h"
#include "llama-memory.h"
#include <set>
#include <vector>
@ -13,7 +13,7 @@
// TODO: extract the KV cache state used for graph computation into llama_kv_cache_recurrent_state_i
// see the implementation of llama_kv_cache_unified_state_i for an example how to do it
class llama_kv_cache_recurrent : public llama_kv_cache {
class llama_kv_cache_recurrent : public llama_memory_i {
public:
llama_kv_cache_recurrent(
const llama_model & model,
@ -29,7 +29,17 @@ public:
// llama_memory_i
//
void clear() override;
llama_memory_state_ptr init_batch(
const llama_batch & batch,
uint32_t n_ubatch,
bool embd_pooled,
bool logits_all) override;
llama_memory_state_ptr init_full() override;
llama_memory_state_ptr init_update(llama_context * lctx, bool optimize) override;
void clear(bool data) override;
bool seq_rm (llama_seq_id seq_id, llama_pos p0, llama_pos p1) override;
void seq_cp (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) override;
@ -40,22 +50,6 @@ public:
llama_pos seq_pos_min(llama_seq_id seq_id) const override;
llama_pos seq_pos_max(llama_seq_id seq_id) const override;
//
// llama_kv_cache
//
llama_memory_state_ptr init_batch(
const llama_batch & batch,
uint32_t n_ubatch,
bool embd_pooled,
bool logits_all) override;
llama_memory_state_ptr init_full() override;
bool update(llama_context & lctx) override;
void defrag_sched(float thold) override;
bool prepare(const std::vector<llama_ubatch> & ubatches);
// find a contiguous slot of kv cells and emplace the ubatch there