Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 08:44:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'deae5ee133a3c4c56fbd46c17c8c2103af3bd643' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/openvino.Dockerfile
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/docker.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.github/workflows/ui-build-self-hosted.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui-publish.yml
#	.github/workflows/ui-self-hosted.yml
#	.github/workflows/ui.yml
#	CMakeLists.txt
#	docs/backend/snapdragon/CMakeUserPresets.json
#	docs/backend/snapdragon/README.md
#	docs/backend/snapdragon/developer.md
#	docs/backend/snapdragon/linux.md
#	docs/backend/snapdragon/windows.md
#	docs/ops.md
#	docs/ops/Vulkan.csv
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.h
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-opnode.h
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/dma-queue.h
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp-tensor.c
#	ggml/src/ggml-hexagon/htp/htp-tensor.h
#	ggml/src/ggml-hexagon/htp/hvx-arith.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-rpc/CMakeLists.txt
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/snapdragon/ggml-hexagon-trace.py
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/rpc/README.md
#	tools/server/README.md
#	tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-08-28 19:31:29 +08:00
parent f178512db3 deae5ee133
commit ae60e1d6e0
328 changed files with 4599 additions and 2556 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+34 -11
View File
@@ -2645,6 +2645,27 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.mtmd_batch_max_tokens = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MTMD_BATCH_MAX_TOKENS"));
add_opt(common_arg(
{"--video-fps"}, "N",
string_format("target video frame rate (default: %.1f)", params.video_fps),
[](common_params & params, const std::string & value) {
params.video_fps = std::stof(value);
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_VIDEO_FPS"));
add_opt(common_arg(
{"--video-timestamp-interval"}, "N",
string_format("interval in milliseconds between text timestamps (default: %" PRId64 ")", params.video_timestamp_interval_ms),
[](common_params & params, int value) {
params.video_timestamp_interval_ms = value;
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_VIDEO_TIMESTAMP_INTERVAL"));
add_opt(common_arg(
{"--video-ffmpeg-dir"}, "DIR",
"path to the directory containing ffmpeg and ffprobe (default: search in PATH)",
[](common_params & params, const std::string & value) {
params.video_ffmpeg_bin_dir = value;
}
).set_examples(mmproj_examples).set_env("LLAMA_ARG_VIDEO_FFMPEG_DIR"));
if (params.is_gen_docs || llama_supports_rpc()) {
add_opt(common_arg(
{"--rpc"}, "SERVERS",
@@ -2751,14 +2772,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
if (value < 0) {
throw std::invalid_argument("invalid value");
}
for (int i = 0; i < value; ++i) {
// keep strings alive and avoid leaking memory by storing them in a static vector
static std::list<std::string> buft_overrides;
buft_overrides.push_back(llm_ffn_exps_block_regex(i));
params.tensor_buft_overrides.push_back({buft_overrides.back().c_str(), ggml_backend_cpu_buffer_type()});
}
llm_add_n_cpu_ffn_overrides(value, LLM_FFN_EXPS_REGEX, params.tensor_buft_overrides);
}
).set_env("LLAMA_ARG_N_CPU_MOE"));
add_opt(common_arg(
{"-ncffn", "--n-cpu-ffn"}, "N",
"keep the dense FFN weights of the first N layers in the CPU\n"
"(dense models; for MoE expert weights use --n-cpu-moe)",
[](common_params & params, int value) {
if (value < 0) {
throw std::invalid_argument("invalid value");
}
llm_add_n_cpu_ffn_overrides(value, LLM_FFN_DENSE_REGEX, params.tensor_buft_overrides);
}
).set_env("LLAMA_ARG_N_CPU_FFN"));
GGML_ASSERT(params.n_gpu_layers < 0); // string_format would need to be extended for a default >= 0
add_opt(common_arg(
{"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
@@ -4085,11 +4112,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
if (value < 0) {
throw std::invalid_argument("invalid value");
}
for (int i = 0; i < value; ++i) {
static std::list<std::string> buft_overrides_draft;
buft_overrides_draft.push_back(llm_ffn_exps_block_regex(i));
params.speculative.draft.tensor_buft_overrides.push_back({buft_overrides_draft.back().c_str(), ggml_backend_cpu_buffer_type()});
}
llm_add_n_cpu_ffn_overrides(value, LLM_FFN_EXPS_REGEX, params.speculative.draft.tensor_buft_overrides);
}
).set_spec().set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_SPEC_DRAFT_N_CPU_MOE"));