perf: raise frank-default-large to batch 8192 / ubatch 2048

Empirically verified on 2026-08-13 (caches dropped): batch 8192 / ubatch
2048 loads and serves at ctx 602100 with 61 GiB VRAM peak. The benchmark
doc's 'ubatch 2048 OOMs' results were confounded by page-cache pressure -
with the model's pages fully cached the KV/graph allocation stalls at
28 GiB VRAM. Drop caches (sync; echo 3 > /proc/sys/vm/drop_caches) before
starting a load to make restarts reliable.

scripts/serve-llama-frank-large.sh

@@ -35,8 +35,8 @@ fi
 : "${N_GPU_LAYERS:=all}"
 : "${CACHE_TYPE_K:=q8_0}"
 : "${CACHE_TYPE_V:=q8_0}"
-: "${BATCH_SIZE:=2048}"
-: "${UBATCH_SIZE:=512}"
+: "${BATCH_SIZE:=8192}"
+: "${UBATCH_SIZE:=2048}"
 : "${TEMPERATURE:=1.0}"
 : "${TOP_K:=20}"
 : "${TOP_P:=0.95}"