common: infer the speculative type from the draft repo sidecars (#25989)

With -hfd pointing to a repo that ships mtp-/dflash-/eagle3- sidecars
and no --spec-type given, the draft resolved to a full model while the
sidecar was the intended draft.

When the speculative types are still at their default, discover the
sidecars of the draft repo, pick the first available following the
existing mtp > dflash > eagle3 priority, and set the corresponding
type, so this now works without any extra flag:

llama-server -hf repo:Q3_K_M -hfd repo:Q8_0

An explicit --spec-type disables the inference, and a draft repo
without sidecars keeps resolving to a full model as before.

diff --git a/common/arg.cpp b/common/arg.cpp
index 48e274774231531936257fabfbb1262916436f65..1f5b5a8abfc95090a14bfa98613ef47929fd3f02 100644 (file)
--- a/common/arg.cpp
+++ b/common/arg.cpp
@@ -351,6 +351,10 @@ static std::string get_default_local_path(const std::string & url) {
     return fs_get_cache_file(string_split<std::string>(f, '/').back());
 }
 
+static bool spec_types_is_default(const common_params & params) {
+    return params.speculative.types == std::vector<enum common_speculative_type>{COMMON_SPECULATIVE_TYPE_NONE};
+}
+
 common_models_handler common_models_handler_init(const common_params & params, llama_example curr_ex) {
     common_download_hf_plan plan;
     common_download_hf_plan plan_spec;
@@ -391,7 +395,14 @@ common_models_handler common_models_handler_init(const common_params & params, l
     }
 
     if (!params.speculative.draft.mparams.hf_repo.empty()) {
-        plan_spec = common_download_get_hf_plan(params.speculative.draft.mparams, opts);
+        // without a requested type, discover every sidecar the draft repo ships to infer the type later
+        auto opts_spec = opts;
+        if (spec_types_is_default(params)) {
+            opts_spec.download_mtp    = true;
+            opts_spec.download_dflash = true;
+            opts_spec.download_eagle3 = true;
+        }
+        plan_spec = common_download_get_hf_plan(params.speculative.draft.mparams, opts_spec);
     }
 
     if (!params.vocoder.model.hf_repo.empty()) {
@@ -527,6 +538,20 @@ void common_models_handler_apply(common_models_handler & handler, common_params
         }
     };
 
+    // infer the speculative type from the sidecar shipped by the draft repo when none is requested
+    if (spec_types_is_default(params)) {
+        if (!plan_spec.mtp.local_path.empty()) {
+            params.speculative.types = { COMMON_SPECULATIVE_TYPE_DRAFT_MTP };
+            plan_spec.dflash = {};
+            plan_spec.eagle3 = {};
+        } else if (!plan_spec.dflash.local_path.empty()) {
+            params.speculative.types = { COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH };
+            plan_spec.eagle3 = {};
+        } else if (!plan_spec.eagle3.local_path.empty()) {
+            params.speculative.types = { COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3 };
+        }
+    }
+
     // when a sidecar type is requested, the draft repo resolves to its sidecar instead of a full model
     const bool spec_sidecar_found = !plan_spec.mtp.local_path.empty() ||
                                     !plan_spec.dflash.local_path.empty() ||