public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-05 05:51:22 +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 19:23:56 +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
examples/talk-llama/llama-hparams.cpp
+7 -1
View File
@@ -71,9 +71,15 @@ uint32_t llama_hparams::n_embd_r() const {
return token_shift_count * n_embd;
}
if (n_shortconv_l_cache != 0) {
// for LFM2 models
return n_embd * (n_shortconv_l_cache - 1);
}
// TODO: maybe support other convolution strides than 1
// NOTE: since the first column of the conv_state is shifted out each time, it's not actually needed
return (ssm_d_conv > 0 ? ssm_d_conv - 1 : 0) * ssm_d_inner;
// Corresponds to Mamba's conv_states size
return (ssm_d_conv > 0 ? ssm_d_conv - 1 : 0) * (ssm_d_inner + 2*ssm_n_group*ssm_d_state);
}
uint32_t llama_hparams::n_embd_s() const {