Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '157b81fe6dbfec7d7ce91ef7cd9c6bc0c218d6fe' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/rocm.Dockerfile
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/build-sanitize.yml
#	.github/workflows/release.yml
#	README.md
#	ci/run.sh
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/concat.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/conv2d.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/conv2d_dw.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/im2col.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/rms_norm_mul.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/row_norm.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/soft_max.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/solve_tri.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts
#	tools/ui/src/lib/hooks/use-models-selector.svelte.ts
#	tools/ui/src/lib/hooks/use-tools-panel.svelte.ts
#	tools/ui/src/lib/services/chat.service.ts
#	tools/ui/svelte.config.js
#	tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-08-10 21:05:07 +08:00
parent 59d92956f7 157b81fe6d
commit 910500e78f
566 changed files with 10579 additions and 6163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+10
View File
@@ -3309,6 +3309,16 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.server_tools = parse_csv_row(value);
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_TOOLS"));
add_opt(common_arg(
{"--tools-runtime"}, "OPTION",
"experimental: run tools in a separate runtime environment (default: none, use host environment)\n"
"available options:\n"
" 'docker:<image>': spin up a new Docker container and reuse it for all invocations, clean up on server exit\n"
" 'docker-container:<id>': use an existing Docker container by ID, won't stop on server exit\n",
[](common_params & params, const std::string & value) {
params.server_tools_runtime = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_TOOLS_RUNTIME"));
add_opt(common_arg(
{"--mcp-servers-config"}, "PATH",
"experimental: path to JSON file with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)\n"