frank-default-small: KV K+V to f16, add verbosity tunable (F16 KV diag)

F16 K removes the flash-attn F16-conversion workspace (MMA_F16 prefill
kernel needs no copy when K is already f16). Trades static KV pool size
for the context-proportional workspace growth implicated in the
cublasSgemm_v2 crash class. VERBOSITY=4 run logs real allocation sizes;
refit CTX_SIZE if the pool does not fit on the 24 GiB 3090.

scripts/serve-llama-frank-small.sh

@@ -30,8 +30,9 @@ fi
 : "${NGRAM_MOD_N_MIN:=48}"
 : "${NGRAM_MOD_N_MAX:=64}"
 : "${NGRAM_MOD_N_MATCH:=24}"
-: "${CACHE_TYPE_K:=q8_0}"
+: "${CACHE_TYPE_K:=f16}"
 : "${CACHE_TYPE_V:=f16}"
+: "${VERBOSITY:=3}"
 : "${N_CPU_MOE:=36}"     # 36 of 40 layers: MoE expert weights stay on CPU; 4 on GPU
 : "${N_GPU_LAYERS:=all}" # every non-expert tensor goes to GPU
 : "${BATCH_SIZE:=2048}"
@@ -66,6 +67,7 @@ exec "$LLAMA_SERVER" \
     --spec-ngram-mod-n-match "$NGRAM_MOD_N_MATCH" \
     --cache-type-k "$CACHE_TYPE_K" \
     --cache-type-v "$CACHE_TYPE_V" \
+    --verbosity "$VERBOSITY" \
     --ctx-size "$CTX_SIZE" \
     --parallel "$PARALLEL" \
     --n-cpu-moe "$N_CPU_MOE" \