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.

docs/LLM/ikllama-ornith-dankserver.md

@@ -1,7 +1,7 @@
 ---
 type: reference
 title: ik_llama.cpp on Dankserver (Ornith Q6_K)
-description: ikawrakow/ik_llama.cpp replaces upstream llama.cpp for frank-default-small on the RTX 3090. q8_0 KV cache with Hadamard (the fast q8_KV type crashes on this arch at this commit), split-mode none (graph requires >=2 GPUs), speculative decoding disabled (3 parallel slots), and explicit CPU-expert offload. Includes the mandatory CUDA/IQK FA_ALL_QUANTS build flags.
+description: ikawrakow/ik_llama.cpp replaces upstream llama.cpp for frank-default-small on the RTX 3090. q8_0 KV cache with Hadamard (the fast q8_KV type crashes on this arch at this commit), split-mode none (graph requires >=2 GPUs), speculative decoding disabled (3 parallel slots), the Qwen-Sharp template rendered with --jinja, and explicit CPU-expert offload. Includes the mandatory CUDA/IQK FA_ALL_QUANTS build flags.
 tags:
   - ikllama
   - llamacpp
@@ -144,17 +144,38 @@ cache RAM vs f16.
 > single-GPU host you must use `none` (or `layer`, which also needs >1).
 > Do not assume `--split-mode graph` degrades gracefully on one GPU.
 
-### Expert offload (MoE on CPU)
+### Expert offload (MoE: CPU with a partial GPU slice)
 
-The expert-offload pattern is unchanged from upstream llama.cpp: the
+The expert-offload pattern from upstream llama.cpp carries over: the
 `--override-tensor` regex pins the sparse expert (`ffn_*_exps`) tensors to
 the CPU buft, leaving every full-attention block plus blocks 35-40 on CUDA.
+On 2026-08-26 we brought expert blocks **30, 32, 33, 34 back to CUDA**
+(~2.5 GiB) to use the ~5.4 GiB GPU headroom for lower latency; the rest of
+that CPU range stays on CPU.
 
-- `OVERRIDE_EXPERT` — the layer-bounded regex (same as before the switch).
+- `OVERRIDE_EXPERT` — the layer-bounded regex listing only the blocks whose
+  experts stay on CPU: `(0|1|2|4|5|6|8|9|10|12|13|14|16|17|18|20|21|22|
+  24|25|26|28|29)`. Blocks 30,32,33,34 (and the always-on full-attention +
+  35-40 set) are left off the list so their experts load to CUDA.
 - `OVERRIDE_BUFT=CPU`.
 - `N_GPU_LAYERS=999` — ik_llama `-ngl` / `--gpu-layers` only accepts an
   integer (the literal `all` is rejected). 999 means "load as many tensor
-  layers as possible", while the expert override still pins the exps to CPU.
+  layers as possible", while the expert override still pins the listed exps
+  to CPU.
+
+To move more experts back to the GPU later, drop more block numbers from
+`OVERRIDE_EXPERT` (each block is ~630 MiB; verify `nvidia-smi` headroom
+first and keep ~2-3 GiB margin for KV/compute).
+
+### Qwen-Sharp chat template via --jinja
+
+`--chat-template-file` alone only stores the template text; ik_llama **does
+not** render a custom template as real Jinja unless `--jinja` is also given
+(`inputs.use_jinja ? common_chat_templates_apply_jinja : <non-jinja
+fallback>`). Without `--jinja` it warns it only supports "commonly used
+templates" and silently uses built-in handlers, dropping the Qwen-Sharp
+template's thinking / image / tool formatting. So the serve script passes
+both `--chat-template-file` and `--jinja` (gated on `USE_JINJA`, set to `1`).
 
 ### Speculative decoding: disabled (3 parallel slots)