vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-10 04:00:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	Makefile
#	README.md
#	docs/backend/SYCL.md
#	examples/llava/README.md
#	examples/llava/clip.cpp
#	examples/run/run.cpp
#	examples/server/README.md
#	examples/sycl/run-llama2.sh
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2025-02-26 18:44:45 +08:00
commit 722fc2dbf1
79 changed files with 9330 additions and 5299 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/llama.h
View file

@ -479,6 +479,7 @@ extern "C" {
LLAMA_API int32_t llama_model_n_embd (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_layer (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_head (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_head_kv (const struct llama_model * model);
// Get the model's RoPE frequency scaling factor
LLAMA_API float llama_model_rope_freq_scale_train(const struct llama_model * model);