LLM inference in C/C++
C++ ggml
speculative : refactor enabled configs common_speculative_init (#26510)
Daniel Bevenius7bd8282c37fc
diff --git a/common/speculative.cpp b/common/speculative.cppindex 514fe85218..70dc0ac3b1 100644--- a/common/speculative.cpp+++ b/common/speculative.cpp@@ -2385,57 +2385,28 @@ common_speculative * common_speculative_init(common_params_speculative & params,{uint32_t enabled_configs = common_get_enabled_speculative_configs(params.types);- bool has_draft_simple = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE));- bool has_draft_eagle3 = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3)) && params.draft.ctx_dft != nullptr;- bool has_draft_mtp = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_MTP)) && params.draft.ctx_dft != nullptr;- bool has_draft_dflash = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH)) && params.draft.ctx_dft != nullptr;- bool has_draft_dspark = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK)) && params.draft.ctx_dft != nullptr;---- bool has_ngram_cache = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_CACHE));- bool has_ngram_simple = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE));- bool has_ngram_map_k = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K));- bool has_ngram_map_k4v = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V));- bool has_ngram_mod = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MOD));+ auto add_config_if_enabled = [&](common_speculative_type type, bool available = true) {+ if (available && (enabled_configs & (1u << type))) {+ configs.emplace_back(type, params);+ }+ };// when adding a new type - update here the logic abovestatic_assert(COMMON_SPECULATIVE_TYPE_COUNT == 11);// this list here defines the priority of the speculators// the one with highest priority are listed first- if (has_ngram_simple) {- // This implementation can guess a lot of tokens without any draft model.- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE, params));- }- if (has_ngram_map_k) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K, params));- }- if (has_ngram_map_k4v) {- // This implementation can guess tokens with high acceptance rate but is more expensive.- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V, params));- }- if (has_ngram_mod) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MOD, params));- }- if (has_ngram_cache) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_CACHE, params));- }- if (has_draft_simple) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE, params));- }- if (has_draft_eagle3) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, params));- }- if (has_draft_mtp) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_MTP, params));- }- if (has_draft_dflash) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, params));- }- if (has_draft_dspark) {- configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, params));- }+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MOD);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_CACHE);++ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, params.draft.ctx_dft != nullptr);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_MTP, params.draft.ctx_dft != nullptr);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, params.draft.ctx_dft != nullptr);+ add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, params.draft.ctx_dft != nullptr);}std::vector<std::unique_ptr<common_speculative_impl>> impls = {};