frank-default-small: render Qwen-Sharp via --jinja; pull more experts to GPU

--jinja: ik_llama only renders a custom --chat-template-file as real Jinja
when --jinja is passed (inputs.use_jinja ? apply_jinja : non-jinja
fallback). Without it the Qwen-Sharp template's thinking/image/tool
formatting is silently dropped. Add USE_JINJA=1 -> --jinja.

Experts: the RTX 3090 had ~5.4 GiB headroom; pull expert blocks 30,32,33,34
back to CUDA (each block ~630 MiB) from CPU for lower latency. Update the
OVERRIDE_EXPERT regex, its test, and the KB with the headroom-check note.

scripts/frank-default-small.env

@@ -34,6 +34,10 @@ LLAMA_SERVER=/home/dank/ik_llama.cpp/build/bin/llama-server
 # staged on the host).
 # Source: https://huggingface.co/peculiar-ragdoll/Qwen-Sharp-Chat-Templates
 CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
+# Render the Qwen-Sharp template with the true Jinja engine (--jinja). Without
+# it ik_llama falls back to built-in non-Jinja handlers and drops the custom
+# template's thinking/image/tool formatting.
+USE_JINJA=1
 
 ALIAS=frank-default-small
 BIND_ADDR=0.0.0.0
@@ -60,7 +64,11 @@ SPEC_TYPE=none
 # 3,7,11,15,19,23,27,31,35,36,37,38,39,40. Move all other expert tensors to
 # CPU. All non-expert tensors stay on the 24 GB card. Buffer type "CPU" is the
 # CPU buft name on this host.
-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'
+#
+# 2026-08-26: brought back expert blocks 30,32,33,34 to CUDA (~2.5 GiB) to
+# use the ~5.4 GiB GPU headroom for lower latency; the remaining larger-CPU
+# range below those stays on CPU.
+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)\.ffn_(up|down|gate|gate_up)_(ch|)exps'
 OVERRIDE_BUFT=CPU
 # ik_llama --gpu-layers/-ngl does NOT accept the literal "all"; use 999 to
 # mean "load as many layers as possible". Expert exps are pinned to CPU by

scripts/serve-frank-small.sh

@@ -45,6 +45,11 @@ fi
 : "${MMPROJ_FILE:=mmproj-Ornith-1.5-35B-A3B-f16.gguf}"
 : "${LLAMA_SERVER:=/home/dank/llama.cpp/build/bin/llama-server}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
+# Render the Qwen-Sharp template with the true Jinja engine. ik_llama only
+# applies --chat-template-file as real Jinja when --jinja is passed;
+# otherwise it falls back to built-in non-Jinja handlers and silently drops
+# the custom template's thinking/image/tool formatting.
+: "${USE_JINJA:=1}"
 : "${ALIAS:=frank-default-small}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
@@ -92,6 +97,7 @@ exec "$LLAMA_SERVER" \
     --model "$MODEL" \
     --mmproj "$MMPROJ" \
     --chat-template-file "$CHAT_TEMPLATE_FILE" \
+    $([ "$USE_JINJA" = "1" ] && printf -- "--jinja") \
     --spec-type "$SPEC_TYPE" \
     --override-tensor "$OVERRIDE_EXPERT=$OVERRIDE_BUFT" \
     --cache-type-k "$CACHE_TYPE_K" \