vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge commit '280345968d' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/main-cuda.Dockerfile
#	.devops/nix/package.nix
#	.devops/server-cuda.Dockerfile
#	.github/workflows/build.yml
#	CMakeLists.txt
#	Makefile
#	README.md
#	ci/run.sh
#	docs/token_generation_performance_tips.md
#	flake.lock
#	llama.cpp
#	scripts/LlamaConfig.cmake.in
#	scripts/compare-commits.sh
#	scripts/server-llm.sh
#	tests/test-quantize-fns.cpp
This commit is contained in:
Concedo 2024-04-07 20:27:17 +08:00
commit a530afa1e4
33 changed files with 124 additions and 1280 deletions
Download patch file Download diff file Expand all files Collapse all files

4
otherarch/gpt2_v3.cpp
View file

@ -16,7 +16,7 @@
#include "model_adapter.h"
#ifdef GGML_USE_CUBLAS
#ifdef GGML_USE_CUDA
#include "ggml_v3-cuda.h"
#endif
#if defined(GGML_USE_CLBLAST)
@ -353,7 +353,7 @@ ModelLoadResult gpt2_model_load(const std::string & fname, gpt2_model & model, g
fin.close();
//gpu offload
#if defined(GGML_USE_CLBLAST) || defined(GGML_USE_CUBLAS)
#if defined(GGML_USE_CLBLAST) || defined(GGML_USE_CUDA)
if(gpulayers>0)
{
const auto & hparams = model.hparams;