Use ngram-mod and prioritize attention experts

tests/frank_small_config.bats

@@ -20,15 +20,38 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
     grep -q '^PARALLEL=3$' "$ENV_FILE"
 }
 
-@test "frank-default-small uses the measured hybrid expert placement" {
-    override=$(grep '^OVERRIDE_EXPERT=' "$ENV_FILE")
-    [[ "$override" == *'26|28|29|30|32)'* ]]
-    [[ "$override" != *'27'* ]]
-    [[ "$override" != *'31'* ]]
-    [[ "$override" != *'33'* ]]
-    [[ "$override" != *'40'* ]]
-    grep -q '^OVERRIDE_BUFT=CPU$' "$ENV_FILE"
-    grep -q '^N_GPU_LAYERS=all$' "$ENV_FILE"
+@test "frank-default-small keeps full-attention and final blocks on CUDA" {
+    source "$ENV_FILE"
+    [[ "$OVERRIDE_EXPERT" == 'blk\.(0|1|2|4|5|6|8|9|10|12|13|14|16|17|18|20|21|22|24|25|26|28|29|30|32|33|34)\.ffn_(up|down|gate|gate_up)_(ch|)exps' ]]
+    [[ "$OVERRIDE_EXPERT" != *'|3|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|7|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|11|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|15|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|19|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|23|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|27|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|31|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|35|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|36|'* ]]
+    [[ "$OVERRIDE_EXPERT" != *'|40|'* ]]
+    [[ "$OVERRIDE_BUFT" == CPU ]]
+    [[ "$N_GPU_LAYERS" == all ]]
+}
+
+@test "frank-default-small uses ngram-mod without MTP" {
+    grep -q '^SPEC_TYPE=ngram-mod$' "$ENV_FILE"
+    grep -q '^SPEC_NGRAM_MOD_N_MIN=48$' "$ENV_FILE"
+    grep -q '^SPEC_NGRAM_MOD_N_MAX=64$' "$ENV_FILE"
+    grep -q '^SPEC_NGRAM_MOD_N_MATCH=24$' "$ENV_FILE"
+    ! grep -q -- 'SPEC_DRAFT_' "$ENV_FILE"
+    ! grep -q -- '--spec-type.*draft-mtp' "$SERVE_FILE"
+    grep -q -- '--spec-ngram-mod-n-max' "$SERVE_FILE"
+}
+
+@test "frank-default-small uses ubatch 1024" {
+    grep -q '^BATCH_SIZE=4096$' "$ENV_FILE"
+    grep -q '^UBATCH_SIZE=1024$' "$ENV_FILE"
+    grep -q ': "${UBATCH_SIZE:=1024}"' "$SERVE_FILE"
 }
 
 @test "frank-default-small uses the tracked Qwen-Sharp template" {