Skip to content

arg: fix order to use short form before long form #18196

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ServeurpersoCom wants to merge 5 commits into
base: master
Choose a base branch
from
+46 −22
Open

arg: fix order to use short form before long form #18196

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
415692e
arg: fix order to use short form before long form
ServeurpersoCom Dec 19, 2025
dc60392
arg: update doc
ServeurpersoCom Dec 19, 2025
4d0d1c2
arg: update test-arg-parser
ServeurpersoCom Dec 19, 2025
724f007
arg: address review feedback from ngxson
ServeurpersoCom Dec 19, 2025
f5e7ebf
arg: update doc
ServeurpersoCom Dec 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 11 additions & 11 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1139,15 +1139,15 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_CTX_CHECKPOINTS").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--cache-ram", "-cram"}, "N",
{"-cram", "--cache-ram"}, "N",
string_format("set the maximum cache size in MiB (default: %d, -1 - no limit, 0 - disable)"
"[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)", params.cache_ram_mib),
[](common_params & params, int value) {
params.cache_ram_mib = value;
}
).set_env("LLAMA_ARG_CACHE_RAM").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--kv-unified", "-kvu"},
{"-kvu", "--kv-unified"},
"use single unified KV buffer shared across all sequences (default: enabled if number of slots is auto)",
[](common_params & params) {
params.kv_unified = true;
Expand Down Expand Up @@ -1415,7 +1415,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_sparam());
add_opt(common_arg(
{"--sampling-seq", "--sampler-seq"}, "SEQUENCE",
{"--sampler-seq", "--sampling-seq"}, "SEQUENCE",
string_format("simplified sequence for samplers that will be used (default: %s)", sampler_type_chars.c_str()),
[](common_params & params, const std::string & value) {
params.sampling.samplers = common_sampler_types_from_chars(value);
Expand Down Expand Up @@ -2073,26 +2073,26 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
));
add_opt(common_arg(
{"--override-tensor", "-ot"}, "<tensor name pattern>=<buffer type>,...",
{"-ot", "--override-tensor"}, "<tensor name pattern>=<buffer type>,...",
"override tensor buffer type", [](common_params & params, const std::string & value) {
parse_tensor_buffer_overrides(value, params.tensor_buft_overrides);
}
));
add_opt(common_arg(
{"--override-tensor-draft", "-otd"}, "<tensor name pattern>=<buffer type>,...",
{"-otd", "--override-tensor-draft"}, "<tensor name pattern>=<buffer type>,...",
"override tensor buffer type for draft model", [](common_params & params, const std::string & value) {
parse_tensor_buffer_overrides(value, params.speculative.tensor_buft_overrides);
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--cpu-moe", "-cmoe"},
{"-cmoe", "--cpu-moe"},
"keep all Mixture of Experts (MoE) weights in the CPU",
[](common_params & params) {
params.tensor_buft_overrides.push_back(llm_ffn_exps_cpu_override());
}
).set_env("LLAMA_ARG_CPU_MOE"));
add_opt(common_arg(
{"--n-cpu-moe", "-ncmoe"}, "N",
{"-ncmoe", "--n-cpu-moe"}, "N",
"keep the Mixture of Experts (MoE) weights of the first N layers in the CPU",
[](common_params & params, int value) {
if (value < 0) {
Expand All @@ -2107,14 +2107,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_env("LLAMA_ARG_N_CPU_MOE"));
add_opt(common_arg(
{"--cpu-moe-draft", "-cmoed"},
{"-cmoed", "--cpu-moe-draft"},
"keep all Mixture of Experts (MoE) weights in the CPU for the draft model",
[](common_params & params) {
params.speculative.tensor_buft_overrides.push_back(llm_ffn_exps_cpu_override());
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_CPU_MOE_DRAFT"));
add_opt(common_arg(
{"--n-cpu-moe-draft", "-ncmoed"}, "N",
{"-ncmoed", "--n-cpu-moe-draft"}, "N",
"keep the Mixture of Experts (MoE) weights of the first N layers in the CPU for the draft model",
[](common_params & params, int value) {
if (value < 0) {
Expand Down Expand Up @@ -2642,7 +2642,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_EMBEDDINGS"));
add_opt(common_arg(
{"--reranking", "--rerank"},
{"--rerank", "--reranking"},
string_format("enable reranking endpoint on server (default: %s)", "disabled"),
[](common_params & params) {
params.embedding = true;
Expand Down Expand Up @@ -3113,7 +3113,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE}));
add_opt(common_arg(
{"--draft-max", "--draft", "--draft-n"}, "N",
{"--draft", "--draft-n", "--draft-max"}, "N",
string_format("number of tokens to draft for speculative decoding (default: %d)", params.speculative.n_max),
[](common_params & params, int value) {
params.speculative.n_max = value;
Expand Down
24 changes: 24 additions & 0 deletions tests/test-arg-parser.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,30 @@ int main(void) {
exit(1);
}
}

// ensure shorter argument precedes longer argument
if (opt.args.size() > 1) {
const std::string first(opt.args.front());
const std::string last(opt.args.back());

if (first.length() > last.length()) {
fprintf(stderr, "test-arg-parser: shorter argument should come before longer one: %s, %s\n",
first.c_str(), last.c_str());
assert(false);
}
}

// same check for negated arguments
if (opt.args_neg.size() > 1) {
const std::string first(opt.args_neg.front());
const std::string last(opt.args_neg.back());

if (first.length() > last.length()) {
fprintf(stderr, "test-arg-parser: shorter negated argument should come before longer one: %s, %s\n",
first.c_str(), last.c_str());
assert(false);
}
}
}
} catch (std::exception & e) {
printf("%s\n", e.what());
Expand Down
22 changes: 11 additions & 11 deletions tools/server/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,9 +75,9 @@ For the ful list of features, please refer to [server's changelog](https://githu
| `--numa TYPE` | attempt optimizations that help on some NUMA systems<br/>- distribute: spread execution evenly over all nodes<br/>- isolate: only spawn threads on CPUs on the node that execution started on<br/>- numactl: use the CPU map provided by numactl<br/>if run without this previously, it is recommended to drop the system page cache before using this<br/>see https://github.com/ggml-org/llama.cpp/issues/1437<br/>(env: LLAMA_ARG_NUMA) |
| `-dev, --device <dev1,dev2,..>` | comma-separated list of devices to use for offloading (none = don't offload)<br/>use --list-devices to see a list of available devices<br/>(env: LLAMA_ARG_DEVICE) |
| `--list-devices` | print list of available devices and exit |
| `--override-tensor, -ot <tensor name pattern>=<buffer type>,...` | override tensor buffer type |
| `--cpu-moe, -cmoe` | keep all Mixture of Experts (MoE) weights in the CPU<br/>(env: LLAMA_ARG_CPU_MOE) |
| `--n-cpu-moe, -ncmoe N` | keep the Mixture of Experts (MoE) weights of the first N layers in the CPU<br/>(env: LLAMA_ARG_N_CPU_MOE) |
| `-ot, --override-tensor <tensor name pattern>=<buffer type>,...` | override tensor buffer type |
| `-cmoe, --cpu-moe` | keep all Mixture of Experts (MoE) weights in the CPU<br/>(env: LLAMA_ARG_CPU_MOE) |
| `-ncmoe, --n-cpu-moe N` | keep the Mixture of Experts (MoE) weights of the first N layers in the CPU<br/>(env: LLAMA_ARG_N_CPU_MOE) |
| `-ngl, --gpu-layers, --n-gpu-layers N` | max. number of layers to store in VRAM (default: -1)<br/>(env: LLAMA_ARG_N_GPU_LAYERS) |
| `-sm, --split-mode {none,layer,row}` | how to split the model across multiple GPUs, one of:<br/>- none: use one GPU only<br/>- layer (default): split layers and KV across GPUs<br/>- row: split rows across GPUs<br/>(env: LLAMA_ARG_SPLIT_MODE) |
| `-ts, --tensor-split N0,N1,N2,...` | fraction of the model to offload to each GPU, comma-separated list of proportions, e.g. 3,1<br/>(env: LLAMA_ARG_TENSOR_SPLIT) |
Expand Down Expand Up @@ -120,7 +120,7 @@ For the ful list of features, please refer to [server's changelog](https://githu
| -------- | ----------- |
| `--samplers SAMPLERS` | samplers that will be used for generation in the order, separated by ';'<br/>(default: penalties;dry;top_n_sigma;top_k;typ_p;top_p;min_p;xtc;temperature) |
| `-s, --seed SEED` | RNG seed (default: -1, use random seed for -1) |
| `--sampling-seq, --sampler-seq SEQUENCE` | simplified sequence for samplers that will be used (default: edskypmxt) |
| `--sampler-seq, --sampling-seq SEQUENCE` | simplified sequence for samplers that will be used (default: edskypmxt) |
| `--ignore-eos` | ignore end of stream token and continue generating (implies --logit-bias EOS-inf) |
| `--temp N` | temperature (default: 0.8) |
| `--top-k N` | top-k sampling (default: 40, 0 = disabled)<br/>(env: LLAMA_ARG_TOP_K) |
Expand Down Expand Up @@ -156,8 +156,8 @@ For the ful list of features, please refer to [server's changelog](https://githu
| Argument | Explanation |
| -------- | ----------- |
| `--ctx-checkpoints, --swa-checkpoints N` | max number of context checkpoints to create per slot (default: 8)[(more info)](https://github.com/ggml-org/llama.cpp/pull/15293)<br/>(env: LLAMA_ARG_CTX_CHECKPOINTS) |
| `--cache-ram, -cram N` | set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 - disable)[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)<br/>(env: LLAMA_ARG_CACHE_RAM) |
| `--kv-unified, -kvu` | use single unified KV buffer shared across all sequences (default: enabled if number of slots is auto)<br/>(env: LLAMA_ARG_KV_UNIFIED) |
| `-cram, --cache-ram N` | set the maximum cache size in MiB (default: 8192, -1 - no limit, 0 - disable)[(more info)](https://github.com/ggml-org/llama.cpp/pull/16391)<br/>(env: LLAMA_ARG_CACHE_RAM) |
| `-kvu, --kv-unified` | use single unified KV buffer shared across all sequences (default: enabled if number of slots is auto)<br/>(env: LLAMA_ARG_KV_UNIFIED) |
| `--context-shift, --no-context-shift` | whether to use context shift on infinite text generation (default: disabled)<br/>(env: LLAMA_ARG_CONTEXT_SHIFT) |
| `-r, --reverse-prompt PROMPT` | halt generation at PROMPT, return control in interactive mode<br/> |
| `-sp, --special` | special tokens output enabled (default: false) |
Expand All @@ -172,9 +172,9 @@ For the ful list of features, please refer to [server's changelog](https://githu
| `--mmproj-offload, --no-mmproj-offload` | whether to enable GPU offloading for multimodal projector (default: enabled)<br/>(env: LLAMA_ARG_MMPROJ_OFFLOAD) |
| `--image-min-tokens N` | minimum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MIN_TOKENS) |
| `--image-max-tokens N` | maximum number of tokens each image can take, only used by vision models with dynamic resolution (default: read from model)<br/>(env: LLAMA_ARG_IMAGE_MAX_TOKENS) |
| `--override-tensor-draft, -otd <tensor name pattern>=<buffer type>,...` | override tensor buffer type for draft model |
| `--cpu-moe-draft, -cmoed` | keep all Mixture of Experts (MoE) weights in the CPU for the draft model<br/>(env: LLAMA_ARG_CPU_MOE_DRAFT) |
| `--n-cpu-moe-draft, -ncmoed N` | keep the Mixture of Experts (MoE) weights of the first N layers in the CPU for the draft model<br/>(env: LLAMA_ARG_N_CPU_MOE_DRAFT) |
| `-otd, --override-tensor-draft <tensor name pattern>=<buffer type>,...` | override tensor buffer type for draft model |
| `-cmoed, --cpu-moe-draft` | keep all Mixture of Experts (MoE) weights in the CPU for the draft model<br/>(env: LLAMA_ARG_CPU_MOE_DRAFT) |
| `-ncmoed, --n-cpu-moe-draft N` | keep the Mixture of Experts (MoE) weights of the first N layers in the CPU for the draft model<br/>(env: LLAMA_ARG_N_CPU_MOE_DRAFT) |
| `-a, --alias STRING` | set alias for model name (to be used by REST API)<br/>(env: LLAMA_ARG_ALIAS) |
| `--host HOST` | ip address to listen, or bind to an UNIX socket if the address ends with .sock (default: 127.0.0.1)<br/>(env: LLAMA_ARG_HOST) |
| `--port PORT` | port to listen (default: 8080)<br/>(env: LLAMA_ARG_PORT) |
Expand All @@ -184,7 +184,7 @@ For the ful list of features, please refer to [server's changelog](https://githu
| `--webui-config-file PATH` | JSON file that provides default WebUI settings (overrides WebUI defaults)<br/>(env: LLAMA_ARG_WEBUI_CONFIG_FILE) |
| `--webui, --no-webui` | whether to enable the Web UI (default: enabled)<br/>(env: LLAMA_ARG_WEBUI) |
| `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)<br/>(env: LLAMA_ARG_EMBEDDINGS) |
| `--reranking, --rerank` | enable reranking endpoint on server (default: disabled)<br/>(env: LLAMA_ARG_RERANKING) |
| `--rerank, --reranking` | enable reranking endpoint on server (default: disabled)<br/>(env: LLAMA_ARG_RERANKING) |
| `--api-key KEY` | API key to use for authentication (default: none)<br/>(env: LLAMA_API_KEY) |
| `--api-key-file FNAME` | path to file containing API keys (default: none) |
| `--ssl-key-file FNAME` | path to file a PEM-encoded SSL private key<br/>(env: LLAMA_ARG_SSL_KEY_FILE) |
Expand Down Expand Up @@ -212,7 +212,7 @@ For the ful list of features, please refer to [server's changelog](https://githu
| `--lora-init-without-apply` | load LoRA adapters without applying them (apply later via POST /lora-adapters) (default: disabled) |
| `-td, --threads-draft N` | number of threads to use during generation (default: same as --threads) |
| `-tbd, --threads-batch-draft N` | number of threads to use during batch and prompt processing (default: same as --threads-draft) |
| `--draft-max, --draft, --draft-n N` | number of tokens to draft for speculative decoding (default: 16)<br/>(env: LLAMA_ARG_DRAFT_MAX) |
| `--draft, --draft-n, --draft-max N` | number of tokens to draft for speculative decoding (default: 16)<br/>(env: LLAMA_ARG_DRAFT_MAX) |
| `--draft-min, --draft-n-min N` | minimum number of draft tokens to use for speculative decoding (default: 0)<br/>(env: LLAMA_ARG_DRAFT_MIN) |
| `--draft-p-min P` | minimum speculative decoding probability (greedy) (default: 0.8)<br/>(env: LLAMA_ARG_DRAFT_P_MIN) |
| `-cd, --ctx-size-draft N` | size of the prompt context for the draft model (default: 0, 0 = loaded from model)<br/>(env: LLAMA_ARG_CTX_SIZE_DRAFT) |
Expand Down
Loading