public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-18 21:55:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2026-01-14 09:11:59 +02:00
parent 13dc9a912b
commit ecfcc65fbf
43 changed files with 3208 additions and 668 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/talk-llama/models/models.h
+13 -3
View File
@@ -312,6 +312,10 @@ struct llm_build_llama_iswa : public llm_graph_context {
llm_build_llama_iswa(const llama_model & model, const llm_graph_params & params);
};
struct llm_build_maincoder : public llm_graph_context {
llm_build_maincoder(const llama_model & model, const llm_graph_params & params);
};
struct llm_build_mamba : public llm_graph_context_mamba {
llm_build_mamba(const llama_model & model, const llm_graph_params & params);
};
@@ -332,7 +336,6 @@ struct llm_build_mistral3 : public llm_graph_context {
llm_build_mistral3(const llama_model & model, const llm_graph_params & params);
};
template <bool iswa>
struct llm_build_modern_bert : public llm_graph_context {
llm_build_modern_bert(const llama_model & model, const llm_graph_params & params);
};
@@ -463,7 +466,8 @@ private:
ggml_tensor * cur,
int il);
ggml_tensor * build_delta_net_chunking(
// returns pair of output and new state
std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_chunking(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
@@ -475,7 +479,8 @@ private:
ggml_tensor * diag_mask,
int il);
ggml_tensor * build_delta_net_autoregressive(
// returns pair of output and new state
std::pair<ggml_tensor *, ggml_tensor *> build_delta_net_autoregressive(
ggml_tensor * q,
ggml_tensor * k,
ggml_tensor * v,
@@ -490,6 +495,11 @@ private:
ggml_tensor * gate,
int layer);
// returns pair of qkv, z
std::pair<ggml_tensor *, ggml_tensor *> build_qkvz(
ggml_tensor * input,
int il);
const llama_model & model;
};