CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into finelayer

Browse Source
This commit is contained in:
Jonathan Graehl
2025-08-04 15:44:10 -07:00
committed by GitHub
parent bc39aa67f9 19f68fa5a4
commit 50e83eaed8
178 changed files with 77772 additions and 33766 deletions
Download Patch File Download Diff File Expand all files Collapse all files

87
common/arg.cpp
View File

@@ -977,6 +977,10 @@ static bool common_params_parse_ex(int argc, char ** argv, common_params_context
for (auto & seq_breaker : params.sampling.dry_sequence_breakers) {
string_process_escapes(seq_breaker);
}
for (auto & pair : params.speculative.replacements) {
string_process_escapes(pair.first);
string_process_escapes(pair.second);
}
}
if (!params.kv_overrides.empty()) {
@@ -2092,6 +2096,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.no_kv_offload = true;
}
).set_env("LLAMA_ARG_NO_KV_OFFLOAD"));
add_opt(common_arg(
{"-nr", "--no-repack"},
"disable weight repacking",
[](common_params & params) {
params.no_extra_bufts = true;
}
).set_env("LLAMA_ARG_NO_REPACK"));
add_opt(common_arg(
{"-ctk", "--cache-type-k"}, "TYPE",
string_format(
@@ -2370,6 +2381,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
));
add_opt(common_arg(
{"--cpu-moe"},
"use CPU for Mixture of Experts (MoE) weights",
[](common_params & params) {
params.tensor_buft_overrides.push_back({"\\.ffn_up_exps\\.weight$", ggml_backend_cpu_buffer_type()});
params.tensor_buft_overrides.push_back({"\\.ffn_down_exps\\.weight$", ggml_backend_cpu_buffer_type()});
params.tensor_buft_overrides.push_back({"\\.ffn_gate_exps\\.weight$", ggml_backend_cpu_buffer_type()});
}
).set_env("LLAMA_ARG_CPU_MOE"));
add_opt(common_arg(
{"-ngl", "--gpu-layers", "--n-gpu-layers"}, "N",
"number of layers to store in VRAM",
@@ -2628,6 +2648,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.n_out_freq = value;
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--output-format"}, "{gguf,dat}",
string_format("output format for imatrix file (default: %s)", params.imat_dat > 0 ? "dat" : "gguf"),
[](common_params & params, const std::string & value) {
/**/ if (value == "gguf") { params.imat_dat = -1; }
else if (value == "dat") { params.imat_dat = 1; }
else { throw std::invalid_argument("invalid output format"); }
}
).set_examples({LLAMA_EXAMPLE_IMATRIX}));
add_opt(common_arg(
{"--save-frequency"}, "N",
string_format("save an imatrix copy every N iterations (default: %d)", params.n_save_freq),
@@ -3250,6 +3279,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.model.path = value;
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MODEL_DRAFT"));
add_opt(common_arg(
{"--spec-replace"}, "TARGET", "DRAFT",
"translate the string in TARGET into DRAFT if the draft model and main model are not compatible",
[](common_params & params, const std::string & tgt, const std::string & dft) {
params.speculative.replacements.push_back({ tgt, dft });
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER}));
add_opt(common_arg(
{"-ctkd", "--cache-type-k-draft"}, "TYPE",
string_format(
@@ -3439,28 +3475,11 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SERVER}));
// diffusion parameters
add_opt(common_arg(
{ "--diffusion-steps" }, "N",
string_format("number of diffusion steps (default: %d)", params.diffusion.steps),
[](common_params & params, int value) { params.diffusion.steps = value; }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-eps" }, "F",
string_format("epsilon for timesteps (default: %.6f)", (double) params.diffusion.eps),
[](common_params & params, const std::string & value) { params.diffusion.eps = std::stof(value); }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-algorithm" }, "N",
string_format("diffusion algorithm: 0=ORIGIN, 1=MASKGIT_PLUS, 2=TOPK_MARGIN, 3=ENTROPY (default: %d)",
params.diffusion.algorithm),
[](common_params & params, int value) { params.diffusion.algorithm = value; }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-alg-temp" }, "F",
string_format("algorithm temperature (default: %.3f)", (double) params.diffusion.alg_temp),
[](common_params & params, const std::string & value) { params.diffusion.alg_temp = std::stof(value); }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-visual" },
string_format("enable visual diffusion mode (show progressive generation) (default: %s)",
@@ -3468,6 +3487,40 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) { params.diffusion.visual_mode = true; }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-eps" }, "F",
string_format("epsilon for timesteps (default: %.6f)", (double) params.diffusion.eps),
[](common_params & params, const std::string & value) { params.diffusion.eps = std::stof(value); }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-algorithm" }, "N",
string_format("diffusion algorithm: 0=ORIGIN, 1=ENTROPY_BASED, 2=MARGIN_BASED, 3=RANDOM, 4=LOW_CONFIDENCE (default: %d)",
params.diffusion.algorithm),
[](common_params & params, int value) { params.diffusion.algorithm = value; }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-alg-temp" }, "F",
string_format("dream algorithm temperature (default: %.3f)", (double) params.diffusion.alg_temp),
[](common_params & params, const std::string & value) { params.diffusion.alg_temp = std::stof(value); }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-block-length" }, "N",
string_format("llada block length for generation (default: %d)", params.diffusion.block_length),
[](common_params & params, int value) { params.diffusion.block_length = value; }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-cfg-scale" }, "F",
string_format("llada classifier-free guidance scale (default: %.3f)", (double) params.diffusion.cfg_scale),
[](common_params & params, const std::string & value) { params.diffusion.cfg_scale = std::stof(value); }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(common_arg(
{ "--diffusion-add-gumbel-noise" }, "F",
string_format("add gumbel noise to the logits if temp > 0.0 (default: %s)", params.diffusion.add_gumbel_noise ? "true" : "false"),
[](common_params & params, const std::string & value) { params.diffusion.add_gumbel_noise = std::stof(value); }
).set_examples({ LLAMA_EXAMPLE_DIFFUSION }));
add_opt(
common_arg({ "-lr", "--learning-rate-initial" }, "ALPHA",
string_format(