mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-08-31 01:54:21 +00:00
Merge branch 'upstream' into concedo_experimental
# Conflicts: # .devops/intel.Dockerfile # .github/workflows/build-cross.yml # .github/workflows/build-sycl.yml # .github/workflows/build.yml # .github/workflows/editorconfig.yml # .github/workflows/release.yml # cmake/riscv64-spacemit-linux-gnu-gcc.cmake # docs/backend/OPENVINO.md # docs/backend/SYCL.md # docs/build-riscv64-spacemit.md # docs/ops.md # docs/ops/WebGPU.csv # embd_res/ggml-vocab-qwen35.gguf # embd_res/ggml-vocab-qwen35.gguf.inp # embd_res/ggml-vocab-qwen35.gguf.out # examples/model-conversion/Makefile # ggml/CMakeLists.txt # ggml/src/ggml-cpu/CMakeLists.txt # ggml/src/ggml-hexagon/ggml-hexagon.cpp # ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c # ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c # ggml/src/ggml-hexagon/htp/hmx-utils.h # ggml/src/ggml-hexagon/htp/htp-ops.h # ggml/src/ggml-hexagon/htp/hvx-utils.h # ggml/src/ggml-hexagon/htp/main.c # ggml/src/ggml-hexagon/htp/unary-ops.c # ggml/src/ggml-opencl/CMakeLists.txt # ggml/src/ggml-opencl/ggml-opencl.cpp # ggml/src/ggml-opencl/kernels/cvt.cl # ggml/src/ggml-sycl/CMakeLists.txt # ggml/src/ggml-sycl/common.cpp # ggml/src/ggml-sycl/common.hpp # ggml/src/ggml-sycl/ggml-sycl.cpp # ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp # ggml/src/ggml-webgpu/ggml-webgpu.cpp # ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl # ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_reduce.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl # ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl # ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl # ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl # ggml/src/ggml-zendnn/CMakeLists.txt # ggml/src/ggml-zendnn/ggml-zendnn.cpp # scripts/snapdragon/adb/run-completion.sh # tests/CMakeLists.txt # tools/cli/README.md # tools/completion/README.md # tools/mtmd/clip-impl.h # tools/mtmd/clip.cpp # tools/mtmd/clip.h # tools/server/README.md
This commit is contained in:
Concedo
commit
cc82c3164e
62 changed files with 18693 additions and 7034 deletions
|
|
@ -310,12 +310,14 @@ static bool common_params_handle_remote_preset(common_params & params, llama_exa
|
|||
common_download_opts opts;
|
||||
opts.bearer_token = params.hf_token;
|
||||
opts.offline = params.offline;
|
||||
|
||||
LOG_TRC("%s: looking for remote preset at %s\n", __func__, preset_url.c_str());
|
||||
const int status = common_download_file_single(preset_url, preset_path, opts);
|
||||
const bool has_preset = status >= 200 && status < 400;
|
||||
|
||||
// remote preset is optional, so we don't error out if not found
|
||||
if (has_preset) {
|
||||
LOG_INF("applying remote preset from %s\n", preset_url.c_str());
|
||||
LOG_TRC("%s: applying remote preset from %s\n", __func__, preset_url.c_str());
|
||||
common_preset_context ctx(ex, /* only_remote_allowed */ true);
|
||||
common_preset global;
|
||||
auto remote_presets = ctx.load_from_ini(preset_path, global);
|
||||
|
|
@ -328,7 +330,7 @@ static bool common_params_handle_remote_preset(common_params & params, llama_exa
|
|||
throw std::runtime_error("Remote preset.ini does not contain [" + std::string(hf_tag) + "] section");
|
||||
}
|
||||
} else {
|
||||
LOG_INF("%s", "no remote preset found, skipping\n");
|
||||
LOG_TRC("%s: no remote preset found, skipping\n", __func__);
|
||||
}
|
||||
|
||||
return has_preset;
|
||||
|
|
@ -359,8 +361,7 @@ static handle_model_result common_params_handle_model(struct common_params_model
|
|||
auto download_result = common_download_model(model, opts, true);
|
||||
|
||||
if (download_result.model_path.empty()) {
|
||||
LOG_ERR("error: failed to download model from Hugging Face\n");
|
||||
exit(1);
|
||||
throw std::runtime_error("failed to download model from Hugging Face");
|
||||
}
|
||||
|
||||
model.name = model.hf_repo;
|
||||
|
|
@ -382,8 +383,7 @@ static handle_model_result common_params_handle_model(struct common_params_model
|
|||
opts.offline = offline;
|
||||
auto download_result = common_download_model(model, opts);
|
||||
if (download_result.model_path.empty()) {
|
||||
LOG_ERR("error: failed to download model from %s\n", model.url.c_str());
|
||||
exit(1);
|
||||
throw std::runtime_error("failed to download model from " + model.url);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -437,6 +437,25 @@ static bool parse_bool_value(const std::string & value) {
|
|||
// CLI argument parsing functions
|
||||
//
|
||||
|
||||
void common_params_handle_models(common_params & params, llama_example curr_ex) {
|
||||
auto res = common_params_handle_model(params.model, params.hf_token, params.offline);
|
||||
if (params.no_mmproj) {
|
||||
params.mmproj = {};
|
||||
} else if (res.found_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty()) {
|
||||
// optionally, handle mmproj model when -hf is specified
|
||||
params.mmproj = res.mmproj;
|
||||
}
|
||||
// only download mmproj if the current example is using it
|
||||
for (const auto & ex : mmproj_examples) {
|
||||
if (curr_ex == ex) {
|
||||
common_params_handle_model(params.mmproj, params.hf_token, params.offline);
|
||||
break;
|
||||
}
|
||||
}
|
||||
common_params_handle_model(params.speculative.draft.mparams, params.hf_token, params.offline);
|
||||
common_params_handle_model(params.vocoder.model, params.hf_token, params.offline);
|
||||
}
|
||||
|
||||
static bool common_params_parse_ex(int argc, char ** argv, common_params_context & ctx_arg) {
|
||||
common_params & params = ctx_arg.params;
|
||||
|
||||
|
|
@ -590,22 +609,7 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
|
|||
|
||||
// handle model and download
|
||||
if (!skip_model_download) {
|
||||
auto res = common_params_handle_model(params.model, params.hf_token, params.offline);
|
||||
if (params.no_mmproj) {
|
||||
params.mmproj = {};
|
||||
} else if (res.found_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty()) {
|
||||
// optionally, handle mmproj model when -hf is specified
|
||||
params.mmproj = res.mmproj;
|
||||
}
|
||||
// only download mmproj if the current example is using it
|
||||
for (const auto & ex : mmproj_examples) {
|
||||
if (ctx_arg.ex == ex) {
|
||||
common_params_handle_model(params.mmproj, params.hf_token, params.offline);
|
||||
break;
|
||||
}
|
||||
}
|
||||
common_params_handle_model(params.speculative.draft.mparams, params.hf_token, params.offline);
|
||||
common_params_handle_model(params.vocoder.model, params.hf_token, params.offline);
|
||||
common_params_handle_models(params, ctx_arg.ex);
|
||||
}
|
||||
|
||||
// model is required (except for server)
|
||||
|
|
@ -2221,7 +2225,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
if (llama_supports_rpc()) {
|
||||
add_opt(common_arg(
|
||||
{"--rpc"}, "SERVERS",
|
||||
"comma separated list of RPC servers (host:port)",
|
||||
"comma-separated list of RPC servers (host:port)",
|
||||
[](common_params & params, const std::string & value) {
|
||||
add_rpc_devices(value);
|
||||
GGML_UNUSED(params);
|
||||
|
|
@ -3301,18 +3305,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
).set_env("LLAMA_LOG_VERBOSITY"));
|
||||
add_opt(common_arg(
|
||||
{"--log-prefix"},
|
||||
{"--no-log-prefix"},
|
||||
"Enable prefix in log messages",
|
||||
[](common_params &) {
|
||||
common_log_set_prefix(common_log_main(), true);
|
||||
[](common_params &, bool value) {
|
||||
common_log_set_prefix(common_log_main(), value);
|
||||
}
|
||||
).set_env("LLAMA_LOG_PREFIX"));
|
||||
).set_env("LLAMA_ARG_LOG_PREFIX"));
|
||||
add_opt(common_arg(
|
||||
{"--log-timestamps"},
|
||||
{"--no-log-timestamps"},
|
||||
"Enable timestamps in log messages",
|
||||
[](common_params &) {
|
||||
common_log_set_timestamps(common_log_main(), true);
|
||||
[](common_params &, bool value) {
|
||||
common_log_set_timestamps(common_log_main(), value);
|
||||
}
|
||||
).set_env("LLAMA_LOG_TIMESTAMPS"));
|
||||
).set_env("LLAMA_ARG_LOG_TIMESTAMPS"));
|
||||
|
||||
//
|
||||
// speculative parameters
|
||||
|
|
@ -3553,7 +3559,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
|
|||
).set_spec().set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_SPEC_DRAFT_MODEL"));
|
||||
add_opt(common_arg(
|
||||
{"--spec-type"}, common_speculative_all_types_str(),
|
||||
string_format("type of speculative decoding to use when no draft model is provided (default: %s)\n",
|
||||
string_format("comma-separated list of types of speculative decoding to use (default: %s)\n",
|
||||
common_speculative_type_name_str(params.speculative.types).c_str()),
|
||||
[](common_params & params, const std::string & value) {
|
||||
const auto enabled_types = string_split<std::string>(value, ',');
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue