vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 09:34:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
koboldcpp/examples/gguf-split
History
Concedo 81ac0e5656 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/full-rocm.Dockerfile
#	.devops/full.Dockerfile
#	.devops/llama-cpp-clblast.srpm.spec
#	.devops/llama-cpp-cuda.srpm.spec
#	.devops/llama-cpp.srpm.spec
#	.devops/nix/package.nix
#	.devops/server-cuda.Dockerfile
#	.devops/server-intel.Dockerfile
#	.devops/server-rocm.Dockerfile
#	.devops/server-vulkan.Dockerfile
#	.devops/server.Dockerfile
#	.github/workflows/build.yml
#	.github/workflows/code-coverage.yml
#	.github/workflows/docker.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/gguf-publish.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/server.yml
#	.github/workflows/zig-build.yml
#	CMakeLists.txt
#	Makefile
#	README-sycl.md
#	README.md
#	ci/run.sh
#	examples/gguf-split/gguf-split.cpp
#	flake.lock
#	flake.nix
#	llama.cpp
#	scripts/compare-llama-bench.py
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.last
#	scripts/sync-ggml.sh
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
2024-04-07 22:07:27 +08:00
..
CMakeLists.txt gguf-split: split and merge gguf per batch of tensors (#6135) 2024-03-19 12:05:44 +01:00
gguf-split.cpp Merge branch 'upstream' into concedo_experimental 2024-04-07 22:07:27 +08:00
README.md gguf-split: split and merge gguf per batch of tensors (#6135) 2024-03-19 12:05:44 +01:00

README.md

GGUF split Example

CLI to split / merge GGUF files.

Command line options:

  • --split: split GGUF to multiple GGUF, default operation.
  • --split-max-tensors: maximum tensors in each split: default(128)
  • --merge: merge multiple GGUF to a single GGUF.