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/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
This commit is contained in:
Concedo 2024-04-07 22:07:27 +08:00
commit 81ac0e5656
58 changed files with 32809 additions and 7635 deletions
Download patch file Download diff file Expand all files Collapse all files

7
examples/server/server.cpp
View file

@ -2190,8 +2190,6 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" KV cache defragmentation threshold (default: %.1f, < 0 - disabled)\n", params.defrag_thold);
printf(" -b N, --batch-size N logical maximum batch size (default: %d)\n", params.n_batch);
printf(" -ub N, --ubatch-size N physical maximum batch size (default: %d)\n", params.n_ubatch);
printf(" --memory-f32 use f32 instead of f16 for memory key+value (default: disabled)\n");
printf(" not recommended: doubles context memory required and no measurable increase in quality\n");
if (llama_supports_mlock()) {
printf(" --mlock force system to keep model in RAM rather than swapping or compressing\n");
}
@ -2214,6 +2212,8 @@ static void server_print_usage(const char * argv0, const gpt_params & params, co
printf(" fraction of the model to offload to each GPU, comma-separated list of proportions, e.g. 3,1\n");
printf(" -mg i, --main-gpu i the GPU to use for the model (with split-mode = none),\n");
printf(" or for intermediate results and KV (with split-mode = row)\n");
printf(" -nkvo, --no-kv-offload\n");
printf(" disable KV offload\n");
}
printf(" -m FNAME, --model FNAME\n");
printf(" model path (default: %s)\n", params.model.c_str());
@ -2499,6 +2499,8 @@ static void server_params_parse(int argc, char ** argv, server_params & sparams,
"See main README.md for information on enabling GPU BLAS support",
{{"n_gpu_layers", params.n_gpu_layers}});
}
} else if (arg == "-nkvo" || arg == "--no-kv-offload") {
params.no_kv_offload = true;
} else if (arg == "--split-mode" || arg == "-sm") {
if (++i >= argc) {
invalid_param = true;
@ -3567,6 +3569,7 @@ int main(int argc, char ** argv) {
sigemptyset (&sigint_action.sa_mask);
sigint_action.sa_flags = 0;
sigaction(SIGINT, &sigint_action, NULL);
sigaction(SIGTERM, &sigint_action, NULL);
#elif defined (_WIN32)
auto console_ctrl_handler = +[](DWORD ctrl_type) -> BOOL {
return (ctrl_type == CTRL_C_EVENT) ? (signal_handler(SIGINT), true) : false;