Commit 7804be063 for llama.cpp
commit 7804be0634c578d1da1604a2f2320b33f5a65377
Author: Rudransh Shekhar <kanhaiffco2007@gmail.com>
Date: Mon Nov 16 21:37:45 2026 +0530
arg : allow up to llama_max_devices() configs for --tensor-split and --fit-target (#13293) (#31435)
diff --git a/common/arg.cpp b/common/arg.cpp
index 15cc9abd0..e06cc3617 100644
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -2829,7 +2829,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
const std::regex regex{ R"([,/]+)" };
std::sregex_token_iterator it{ arg_next.begin(), arg_next.end(), regex, -1 };
std::vector<std::string> split_arg{ it, {} };
- if (split_arg.size() >= llama_max_devices()) {
+ if (split_arg.size() > llama_max_devices()) {
throw std::invalid_argument(
string_format("got %zu input configs, but system only has %zu devices", split_arg.size(), llama_max_devices())
);
@@ -2895,7 +2895,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
const std::regex regex{ R"([,/]+)" };
std::sregex_token_iterator it{ arg_next.begin(), arg_next.end(), regex, -1 };
std::vector<std::string> split_arg{ it, {} };
- if (split_arg.size() >= llama_max_devices()) {
+ if (split_arg.size() > llama_max_devices()) {
throw std::invalid_argument(
string_format("got %zu input configs, but system only has %zu devices", split_arg.size(), llama_max_devices())
);
diff --git a/tests/test-arg-parser.cpp b/tests/test-arg-parser.cpp
index 537c33394..843f20709 100644
--- a/tests/test-arg-parser.cpp
+++ b/tests/test-arg-parser.cpp
@@ -333,6 +333,33 @@ static void test(void) {
assert(params.lora_adapters[2].path == "file3\"3\".gguf");
assert(params.lora_adapters[3].path == "file4\".gguf");
+ {
+ std::string ts_exact;
+ for (size_t i = 0; i < llama_max_devices(); ++i) {
+ ts_exact += (i > 0 ? "," : "") + std::to_string(i + 1);
+ }
+ common_params p_ts;
+ argv = {"binary_name", "-m", "model.gguf", "-ts", ts_exact};
+ assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), p_ts, LLAMA_EXAMPLE_COMMON));
+ for (size_t i = 0; i < llama_max_devices(); ++i) {
+ assert(p_ts.tensor_split[i] == static_cast<float>(i + 1));
+ }
+
+ common_params p_fitt;
+ argv = {"binary_name", "-m", "model.gguf", "-fitt", ts_exact};
+ assert(true == common_params_parse(argv.size(), list_str_to_char(argv).data(), p_fitt, LLAMA_EXAMPLE_COMMON));
+ for (size_t i = 0; i < llama_max_devices(); ++i) {
+ assert(p_fitt.fit_params_target[i] == static_cast<size_t>(i + 1) * 1024 * 1024);
+ }
+
+ std::string ts_too_many = ts_exact + ",99";
+ argv = {"binary_name", "-m", "model.gguf", "-ts", ts_too_many};
+ assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), p_ts, LLAMA_EXAMPLE_COMMON));
+
+ argv = {"binary_name", "-m", "model.gguf", "-fitt", ts_too_many};
+ assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), p_fitt, LLAMA_EXAMPLE_COMMON));
+ }
+
// skip this part on windows, because setenv is not supported
#ifdef _WIN32
printf("test-arg-parser: skip on windows build\n");