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 branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/full-cuda.Dockerfile
#	.devops/nix/devshells.nix
#	.devops/nix/nixpkgs-instances.nix
#	.devops/nix/package.nix
#	.devops/nix/scope.nix
#	README.md
#	docs/docker.md
#	examples/llama-bench/llama-bench.cpp
#	flake.lock
#	flake.nix
#	grammars/README.md
#	src/llama.cpp
This commit is contained in:
Concedo 2024-09-06 01:07:31 +08:00
commit 73dca7e5bc
24 changed files with 2747 additions and 666 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -1235,11 +1235,13 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
#endif // GGML_USE_CUDA_SYCL_VULKAN
return true;
}
#ifdef GGML_USE_RPC
if (arg == "--rpc") {
CHECK_ARG
params.rpc_servers = argv[i];
return true;
}
#endif
if (arg == "--no-mmap") {
params.use_mmap = false;
return true;
@ -1930,7 +1932,9 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "*", " --image FILE", "path to an image file. use with multimodal models. Specify multiple times for batching" });
options.push_back({ "backend" });
#ifdef GGML_USE_RPC
options.push_back({ "*", " --rpc SERVERS", "comma separated list of RPC servers" });
#endif
if (llama_supports_mlock()) {
options.push_back({ "*", " --mlock", "force system to keep model in RAM rather than swapping or compressing" });