diff --git a/common/arg.cpp b/common/arg.cpp index 666339a094..cd78a5c643 100644 --- a/common/arg.cpp +++ b/common/arg.cpp @@ -3494,7 +3494,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex throw std::invalid_argument("unknown speculative decoding type without draft model"); } } - ).set_examples({LLAMA_EXAMPLE_SERVER})); + ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_SPEC_TYPE")); add_opt(common_arg( {"--spec-ngram-size-n"}, "N", string_format("ngram size N for ngram-simple/ngram-map speculative decoding, length of lookup n-gram (default: %d)", params.speculative.ngram_size_n),