extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-10 11:37:54 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source
This commit is contained in:
Georgi Gerganov
2025-07-28 10:09:47 +03:00
parent 5b4646df1a
commit d0a9d8c7f8
27 changed files with 3566 additions and 995 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/talk-llama/llama-model.h
View File

@ -99,8 +99,10 @@ enum llm_type {
LLM_TYPE_17B_16E, // llama4 Scout
LLM_TYPE_17B_128E, // llama4 Maverick
LLM_TYPE_A13B,
LLM_TYPE_21B_A3B, // Ernie MoE small
LLM_TYPE_30B_A3B,
LLM_TYPE_235B_A22B,
LLM_TYPE_300B_A47B, // Ernie MoE big
LLM_TYPE_E2B,
LLM_TYPE_E4B,
};
@ -452,10 +454,7 @@ struct llama_model {
llama_memory_i * create_memory(const llama_memory_params & params, llama_cparams & cparams) const;
// TODO: move this to new llm_arch_model_i interface
llm_graph_result_ptr build_graph(
const llm_graph_params & params,
ggml_cgraph * gf,
llm_graph_type type) const;
ggml_cgraph * build_graph(const llm_graph_params & params) const;
private:
struct impl;