vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add llama_model_is_recurrent to simplify figuring that out

Browse source 
This will make it easier to more cleanly support RWKV-v6 and Mamba-2.
This commit is contained in:
Francis Couture-Harpin 2024-08-20 23:55:14 -04:00
parent b264eddbb2
commit 1be5ea7d97
2 changed files with 12 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

3
include/llama.h
View file

@ -508,6 +508,9 @@ extern "C" {
// to the decoder to start generating output sequence. For other models, it returns -1.
LLAMA_API llama_token llama_model_decoder_start_token(const struct llama_model * model);
// Returns true if the model is recurrent (like Mamba, RWKV, etc.)
LLAMA_API bool llama_model_is_recurrent(const struct llama_model * model);
// Returns 0 on success
LLAMA_API uint32_t llama_model_quantize(
const char * fname_inp,