frank-default-small: KV K default f16 (no hadamard), V q6_0 + hadamard

K cache back to default f16 full precision with K_CACHE_HADAMARD=0;
V cache at q6_0 with V_CACHE_HADAMARD=1. Env, serve script, bats, and
KB updated.

scripts/serve-frank-small.sh

@@ -8,9 +8,10 @@
 # Three parallel slots (PARALLEL=3), each with 160000 ctx. Speculative decoding
 # is disabled (ik_llama limits spec to a single slot).
 #
-# KV cache: K q8_0 + V q5_0 with Hadamard transforms (requires a build
-# with GGML_CUDA_FA_ALL_QUANTS=ON + GGML_IQK_FA_ALL_QUANTS=ON; see the env
-# file). q8_KV crashes at init on this arch (ggml.c:5427); q8_0/q5_0 work.#
+# KV cache: K at the default f16 (no Hadamard), V at q6_0 with Hadamard.
+# (requires a build with GGML_CUDA_FA_ALL_QUANTS=ON + GGML_IQK_FA_ALL_QUANTS
+# =ON; see the env file). q8_KV crashes at init on this arch (ggml.c:5427);
+# V uses q6_0 instead.#
 # Split mode is none: Dankserver has a single RTX 3090 and ik_llama rejects
 # split-mode graph with fewer than 2 devices (hard load error).
 
@@ -52,10 +53,10 @@ fi
 : "${CTX_SIZE:=491520}"
 : "${PARALLEL:=3}"
 : "${SPEC_TYPE:=none}"
-: "${CACHE_TYPE_K:=q8_0}"
-: "${CACHE_TYPE_V:=q5_0}"
+: "${CACHE_TYPE_K:=f16}"
+: "${CACHE_TYPE_V:=q6_0}"
 : "${K_CACHE_HADAMARD:=0}"
-: "${V_CACHE_HADAMARD:=0}"
+: "${V_CACHE_HADAMARD:=1}"
 : "${SPLIT_MODE:=none}"
 : "${VERBOSITY:=4}"
 # Expert offload: --override-tensor regex pinned to the CPU buft. Same pattern