extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-09 15:16:08 +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 51cc3924ad
commit 23f9893818
24 changed files with 1456 additions and 430 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
examples/talk-llama/llama-arch.h
View File

@ -46,6 +46,7 @@ enum llm_arch {
LLM_ARCH_GEMMA,
LLM_ARCH_GEMMA2,
LLM_ARCH_GEMMA3,
LLM_ARCH_GEMMA3N,
LLM_ARCH_STARCODER2,
LLM_ARCH_MAMBA,
LLM_ARCH_XVERSE,
@ -79,6 +80,7 @@ enum llm_arch {
LLM_ARCH_BAILINGMOE,
LLM_ARCH_DOTS1,
LLM_ARCH_ARCEE,
LLM_ARCH_ERNIE4_5,
LLM_ARCH_UNKNOWN,
};
@ -269,6 +271,22 @@ enum llm_tensor {
LLM_TENSOR_LAYER_OUT_NORM,
LLM_TENSOR_POST_ATTN_NORM,
LLM_TENSOR_POST_MLP_NORM,
LLM_TENSOR_PER_LAYER_TOKEN_EMBD, // gemma3n
LLM_TENSOR_PER_LAYER_MODEL_PROJ, // gemma3n
LLM_TENSOR_PER_LAYER_INP_GATE, // gemma3n
LLM_TENSOR_PER_LAYER_PROJ, // gemma3n
LLM_TENSOR_PER_LAYER_PROJ_NORM, // gemma3n
LLM_TENSOR_PER_LAYER_POST_NORM, // gemma3n
LLM_TENSOR_ALTUP_PROJ, // gemma3n
LLM_TENSOR_ALTUP_UNEMBD_PROJ, // gemma3n
LLM_TENSOR_ALTUP_CORRECT_COEF, // gemma3n
LLM_TENSOR_ALTUP_CORRECT_SCALE, // gemma3n
LLM_TENSOR_ALTUP_PREDICT_COEF, // gemma3n
LLM_TENSOR_ALTUP_ROUTER, // gemma3n
LLM_TENSOR_ALTUP_ROUTER_NORM, // gemma3n
LLM_TENSOR_LAUREL_L, // gemma3n
LLM_TENSOR_LAUREL_R, // gemma3n
LLM_TENSOR_LAUREL_POST_NORM, // gemma3n
LLM_TENSOR_SSM_IN,
LLM_TENSOR_SSM_CONV1D,
LLM_TENSOR_SSM_X,