Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '34df42f7bef5a711b2b40f5d2b6b78254def99c3' into concedo_experimental

Browse Source 
# Conflicts:
#	README.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/binary-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/htp-msg.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-arith.h
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-inverse.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-hexagon/htp/softmax-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
#	tools/cli/cli.cpp
#	tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte
This commit is contained in:
Concedo
2026-03-10 22:20:04 +08:00
parent 746664fde6 34df42f7be
commit 6adcd0b5db
168 changed files with 15852 additions and 1398 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+16 -1
View File
@@ -1282,13 +1282,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_SWA_FULL"));
add_opt(common_arg(
{"--ctx-checkpoints", "--swa-checkpoints"}, "N",
{"-ctxcp", "--ctx-checkpoints", "--swa-checkpoints"}, "N",
string_format("max number of context checkpoints to create per slot (default: %d)"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)", params.n_ctx_checkpoints),
[](common_params & params, int value) {
params.n_ctx_checkpoints = value;
}
).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),
[](common_params & params, int value) {
params.checkpoint_every_nt = value;
}
).set_env("LLAMA_ARG_CHECKPOINT_EVERY_NT").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"-cram", "--cache-ram"}, "N",
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)"
@@ -2830,6 +2837,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.webui_config_json = read_file(value);
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_WEBUI_CONFIG_FILE"));
add_opt(common_arg(
{"--webui-mcp-proxy"},
{"--no-webui-mcp-proxy"},
string_format("experimental: whether to enable MCP CORS proxy - do not enable in untrusted environments (default: %s)", params.webui_mcp_proxy ? "enabled" : "disabled"),
[](common_params & params, bool value) {
params.webui_mcp_proxy = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_WEBUI_MCP_PROXY"));
add_opt(common_arg(
{"--webui"},
{"--no-webui"},