dankclaw: switch backend to Vulkan0 (48% faster decode at 262k ctx); add bench-high-ctx.sh

scripts/frank-default-large.env

@@ -28,8 +28,12 @@ SPEC_DRAFT_P_MIN=
 SPEC_NGRAM_MOD_N_MIN=48
 SPEC_NGRAM_MOD_N_MAX=64
 SPEC_NGRAM_MOD_N_MATCH=24
-# Backend device from --list-devices. ROCm0 is the production backend.
-DEVICE=ROCm0
+# Backend device from --list-devices. Vulkan0 selected 2026-08-15 for high
+# context: at 262144 ctx (~200k prompt) Vulkan generates ~5.7 t/s vs ROCm
+# ~3.8 t/s (48% faster decode), while ROCm prefills ~12% faster (119 vs 106
+# t/s).  Generation is the interactive cost, so Vulkan0 wins at high ctx.
+# See docs/bench-high-ctx results and [[qwen3.8-spec-matrix]].
+DEVICE=Vulkan0
 # Dense model: full offload. (Not MoE.)
 N_GPU_LAYERS=all
 # KV on GPU, quantized (K q8_0, V q8_0). Keep K == V for Flash Attention;