vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 09:59:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.ecrc
#	CMakePresets.json
#	ci/run.sh
#	docs/backend/SYCL.md
#	ggml/src/CMakeLists.txt
#	src/llama.cpp
#	tests/test-backend-ops.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-08-27 17:46:40 +08:00
commit b2c1ff7a13
30 changed files with 7666 additions and 6889 deletions
Download patch file Download diff file Expand all files Collapse all files

3
include/llama.h
View file

@ -511,6 +511,9 @@ 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,