extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-13 23:49:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk-llama : sync llama.cpp

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-12 16:26:16 +03:00
parent 6d64e4abf3
commit 6ddff4d96a
24 changed files with 2831 additions and 690 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -49,6 +49,9 @@ enum llm_arch {
LLM_ARCH_GEMMA3N,
LLM_ARCH_STARCODER2,
LLM_ARCH_MAMBA,
LLM_ARCH_MAMBA2,
LLM_ARCH_JAMBA,
LLM_ARCH_FALCON_H1,
LLM_ARCH_XVERSE,
LLM_ARCH_COMMAND_R,
LLM_ARCH_COHERE2,
@ -74,6 +77,7 @@ enum llm_arch {
LLM_ARCH_ARWKV7,
LLM_ARCH_GRANITE,
LLM_ARCH_GRANITE_MOE,
LLM_ARCH_GRANITE_HYBRID,
LLM_ARCH_CHAMELEON,
LLM_ARCH_WAVTOKENIZER_DEC,
LLM_ARCH_PLM,
@ -81,6 +85,9 @@ enum llm_arch {
LLM_ARCH_DOTS1,
LLM_ARCH_ARCEE,
LLM_ARCH_ERNIE4_5,
LLM_ARCH_HUNYUAN_MOE,
LLM_ARCH_SMOLLM3,
LLM_ARCH_LFM2,
LLM_ARCH_UNKNOWN,
};
@ -153,7 +160,6 @@ enum llm_kv {
LLM_KV_ATTENTION_SCALE,
LLM_KV_ATTENTION_KEY_LENGTH_MLA,
LLM_KV_ATTENTION_VALUE_LENGTH_MLA,
LLM_KV_ATTENTION_LAYER_INDICES,
LLM_KV_ROPE_DIMENSION_COUNT,
LLM_KV_ROPE_DIMENSION_SECTIONS,
@ -174,6 +180,7 @@ enum llm_kv {
LLM_KV_SSM_CONV_KERNEL,
LLM_KV_SSM_STATE_SIZE,
LLM_KV_SSM_TIME_STEP_RANK,
LLM_KV_SSM_GROUP_COUNT,
LLM_KV_SSM_DT_B_C_RMS,
LLM_KV_WKV_HEAD_SIZE,
@ -221,6 +228,8 @@ enum llm_kv {
LLM_KV_CLASSIFIER_OUTPUT_LABELS,
LLM_KV_SHORTCONV_L_CACHE,
// deprecated:
LLM_KV_TOKENIZER_PREFIX_ID,
LLM_KV_TOKENIZER_SUFFIX_ID,
@ -291,8 +300,12 @@ enum llm_tensor {
LLM_TENSOR_SSM_CONV1D,
LLM_TENSOR_SSM_X,
LLM_TENSOR_SSM_DT,
LLM_TENSOR_SSM_DT_NORM,
LLM_TENSOR_SSM_A,
LLM_TENSOR_SSM_B_NORM,
LLM_TENSOR_SSM_C_NORM,
LLM_TENSOR_SSM_D,
LLM_TENSOR_SSM_NORM,
LLM_TENSOR_SSM_OUT,
LLM_TENSOR_TIME_MIX_W0,
LLM_TENSOR_TIME_MIX_W1,
@ -386,6 +399,9 @@ enum llm_tensor {
LLM_TENSOR_POS_NET_ATTN_K,
LLM_TENSOR_POS_NET_ATTN_V,
LLM_TENSOR_POS_NET_ATTN_OUT,
LLM_TENSOR_SHORTCONV_CONV,
LLM_TENSOR_SHORTCONV_INPROJ,
LLM_TENSOR_SHORTCONV_OUTPROJ,
};
enum llm_tensor_layer {