Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-17 08:19:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'ae251b5ff2634108822e0f8bb20ca4cd5c2c5dcc' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/actions/linux-setup-spacemit/action.yml
#	.github/actions/unarchive-tar/action.yml
#	.github/workflows/build-android.yml
#	.github/workflows/build-cmake-pkg.yml
#	.github/workflows/build-cross.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build.yml
#	.github/workflows/check-vendor.yml
#	.github/workflows/code-style.yml
#	.github/workflows/editorconfig.yml
#	.github/workflows/pre-tokenizer-hashes.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/python-type-check.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui.yml
#	.github/workflows/update-ops-docs.yml
#	ci/run.sh
#	docs/build-riscv64-spacemit.md
#	examples/convert_legacy_llama.py
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/sync_vendor.py
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat.cpp
#	tests/test-gguf.cpp
#	tools/cli/README.md
#	tools/perplexity/perplexity.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2026-05-26 22:01:57 +08:00
parent f9c02610b3 ae251b5ff2
commit 9204f78926
26 changed files with 1134 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+7 -4
View File
@@ -1336,12 +1336,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"-cpent", "--checkpoint-every-n-tokens"}, "N",
string_format("create a checkpoint every n tokens during prefill (processing), -1 to disable (default: %d)", params.checkpoint_every_nt),
{"-cms", "--checkpoint-min-step"}, "N",
string_format("minimum spacing between context checkpoints in tokens (default: %d, 0 = no minimum)", params.checkpoint_min_step),
[](common_params & params, int value) {
params.checkpoint_every_nt = value;
if (value < 0) {
throw std::invalid_argument("checkpoint-min-step must be non-negative");
}
params.checkpoint_min_step = value;
}
).set_env("LLAMA_ARG_CHECKPOINT_EVERY_NT").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
).set_env("LLAMA_ARG_CHECKPOINT_MIN_SPACING_NT").set_examples({LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"-cram", "--cache-ram"}, "N",
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)"