arg: allow -kvu flag for llama-perplexity (#18117)

The -kvu (--kv-unified) flag is required for hellaswag and winogrande
benchmarks which use coupled sequences. Without unified KV cache,
these benchmarks fail with:

  split_equal: sequential split is not supported when there are
  coupled sequences in the input batch (you may need to use the -kvu flag)

This change adds LLAMA_EXAMPLE_PERPLEXITY to the allowed examples for
the -kvu argument, enabling its use with llama-perplexity.

diff --git a/common/arg.cpp b/common/arg.cpp
index f2aec895bacfccc0a5eb33f5c0d6bf3d8e4bba1d..a4ffd5586c023f267238cacf77b73a841649d851 100644 (file)
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -1140,7 +1140,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
         [](common_params & params) {
             params.kv_unified = true;
         }
-    ).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER}));
+    ).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY}));
     add_opt(common_arg(
         {"--context-shift"},
         {"--no-context-shift"},