examples : add --kv-unified to batched example (#18774)

This commit adds the --kv-unified flag to the batched example. This flag
is currently specified in the README.md as required, but is currently
not available as a command line option for the batched example.

The motivation for this is that specifying this flag as the README
instructs, will lead to an error about the flag not being recognized,
and without this option the example fail with the following error:
```console
split_equal: sequential split is not supported when there are coupled
sequences in the input batch (you may need to use the -kvu flag)
decode: failed to find a memory slot for batch of size 4
main: llama_decode() failed
```
This commit is contained in:
Daniel Bevenius 2026-01-12 13:47:58 +01:00 committed by GitHub
parent 8e2da778da
commit 4150da9a95
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 2 deletions

View File

@ -1295,7 +1295,7 @@ 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, LLAMA_EXAMPLE_PERPLEXITY}));
).set_env("LLAMA_ARG_KV_UNIFIED").set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_PERPLEXITY, LLAMA_EXAMPLE_BATCHED}));
add_opt(common_arg(
{"--context-shift"},
{"--no-context-shift"},

View File

@ -80,6 +80,7 @@ int32_t cpu_get_num_math();
//
enum llama_example {
LLAMA_EXAMPLE_BATCHED,
LLAMA_EXAMPLE_DEBUG,
LLAMA_EXAMPLE_COMMON,
LLAMA_EXAMPLE_SPECULATIVE,

View File

@ -21,7 +21,7 @@ int main(int argc, char ** argv) {
params.prompt = "Hello my name is";
params.n_predict = 32;
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_COMMON, print_usage)) {
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_BATCHED, print_usage)) {
return 1;
}