extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-10 06:18:06 +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
2025-06-20 21:18:44 +03:00
parent d65a579a0a
commit e6c10cf3d5
28 changed files with 2521 additions and 1738 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/talk-llama/llama-hparams.cpp
View File

@ -65,7 +65,7 @@ uint32_t llama_hparams::n_embd_v_gqa(uint32_t il) const {
return n_embd_head_v * n_head_kv;
}
uint32_t llama_hparams::n_embd_k_s() const {
uint32_t llama_hparams::n_embd_r() const {
if (wkv_head_size != 0) {
// for RWKV models
return token_shift_count * n_embd;
@ -76,7 +76,7 @@ uint32_t llama_hparams::n_embd_k_s() const {
return (ssm_d_conv > 0 ? ssm_d_conv - 1 : 0) * ssm_d_inner;
}
uint32_t llama_hparams::n_embd_v_s() const {
uint32_t llama_hparams::n_embd_s() const {
if (wkv_head_size != 0) {
// corresponds to RWKV's wkv_states size
return n_embd * wkv_head_size;
@ -86,6 +86,14 @@ uint32_t llama_hparams::n_embd_v_s() const {
return ssm_d_state * ssm_d_inner;
}
bool llama_hparams::is_recurrent(uint32_t il) const {
return recurrent_layer_arr[il];
}
uint32_t llama_hparams::n_pos_per_embd() const {
return rope_type == LLAMA_ROPE_TYPE_MROPE ? 4 : 1;
}
bool llama_hparams::is_swa(uint32_t il) const {
if (il < n_layer) {
return swa_layers[il];