vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '1c641e6aac' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/cloud-v-pipeline
#	.devops/llama-cli-cuda.Dockerfile
#	.devops/llama-cli-rocm.Dockerfile
#	.devops/llama-cli-vulkan.Dockerfile
#	.devops/llama-cli.Dockerfile
#	.devops/llama-cpp-clblast.srpm.spec
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/llama-cpp.srpm.spec
#	.devops/llama-server-cuda.Dockerfile
#	.devops/llama-server-rocm.Dockerfile
#	.devops/llama-server-vulkan.Dockerfile
#	.devops/llama-server.Dockerfile
#	.devops/nix/apps.nix
#	.devops/nix/package.nix
#	.devops/tools.sh
#	.dockerignore
#	.github/ISSUE_TEMPLATE/01-bug-low.yml
#	.github/ISSUE_TEMPLATE/02-bug-medium.yml
#	.github/ISSUE_TEMPLATE/03-bug-high.yml
#	.github/ISSUE_TEMPLATE/04-bug-critical.yml
#	.github/workflows/bench.yml
#	.github/workflows/build.yml
#	.github/workflows/docker.yml
#	.github/workflows/server.yml
#	.gitignore
#	Makefile
#	README-sycl.md
#	README.md
#	ci/run.sh
#	docs/token_generation_performance_tips.md
#	flake.nix
#	grammars/README.md
#	pocs/vdot/CMakeLists.txt
#	scripts/get-hellaswag.sh
#	scripts/get-wikitext-103.sh
#	scripts/get-wikitext-2.sh
#	scripts/get-winogrande.sh
#	scripts/hf.sh
#	scripts/pod-llama.sh
#	scripts/qnt-all.sh
#	scripts/run-all-ppl.sh
#	scripts/run-with-preset.py
#	scripts/server-llm.sh
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-06-14 18:41:37 +08:00
commit b53e760557
94 changed files with 457 additions and 317 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/quantize/CMakeLists.txt
View file

@ -1,4 +1,4 @@
set(TARGET quantize)
set(TARGET llama-quantize)
add_executable(${TARGET} quantize.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE llama common ${CMAKE_THREAD_LIBS_INIT})

6
examples/quantize/tests.sh
View file

@ -18,9 +18,9 @@ fi
set -x
SPLIT=$1/gguf-split
QUANTIZE=$1/quantize
MAIN=$1/main
SPLIT=$1/llama-gguf-split
QUANTIZE=$1/llama-quantize
MAIN=$1/llama-cli
WORK_PATH=$TMP_DIR/quantize
ROOT_DIR=$(realpath $(dirname $0)/../../)