spec : add ngram-mod (#19164)

* spec : add ngram-mod

* cont : simplify + keep track of occupancy

* cont : cleanup

* cont : move initialization to common/speculative

* cont : cleanup

* cont : cleanup

* cont : fix
This commit is contained in:
Georgi Gerganov
2026-01-30 18:21:48 +02:00
committed by GitHub
parent 2e916f996a
commit dabaa2e77a
10 changed files with 292 additions and 29 deletions
+3 -1
View File
@@ -3396,7 +3396,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--spec-type"}, "[none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v]",
{"--spec-type"}, "[none|ngram-cache|ngram-simple|ngram-map-k|ngram-map-k4v|ngram-mod]",
string_format("type of speculative decoding to use when no draft model is provided (default: %s)\n",
common_speculative_type_to_str(params.speculative.type).c_str()),
[](common_params & params, const std::string & value) {
@@ -3410,6 +3410,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K;
} else if (value == "ngram-map-k4v") {
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V;
} else if (value == "ngram-mod") {
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MOD;
} else {
throw std::invalid_argument("unknown speculative decoding type without draft model");
}