frank-medium: pass KV_MEM=0 through as --kv-cache-memory 0

The single-GPU replicas died with torch.OutOfMemoryError during KV
allocation (2.16 GiB requested, 116 MiB free, 29.34 GiB already held by
PyTorch) because the entrypoint blanked KV_MEM=0 into an omitted flag. The
image's patched KV sizing reads an explicit 0 as 'profile this shape'; with
the flag absent vLLM sizes the cache from --gpu-memory-utilization alone and
overshoots. Passing 0 literally is the shape the bench numbers were measured
on, and MAXSEQS gets its default back under set -u.

dankserver/frank-medium/radiance-entrypoint.sh

@@ -27,11 +27,14 @@ set -euo pipefail
 : "${PORT:=7770}"
 : "${SERVED_NAMES:=frank-medium}"
 : "${MAXLEN:=262144}"
-: "${KV_MEM:=18563072000}"
-if [ "$KV_MEM" = "0" ]; then KV_MEM=""; fi   # 0 = let vLLM profile (the launcher's rule)
-: "${CHUNK:=8192}"
-: "${GPU_UTIL:=0.98}"
-: "${TP:=2}"
+: "${MAXSEQS:=8}"
+# KV_MEM=0 is passed THROUGH as --kv-cache-memory 0, which the image's
+# patched KV sizing reads as "profile the shape" (the launcher's rule).
+# Blanking the variable instead omits the flag and makes vLLM size the cache
+# from --gpu-memory-utilization alone: measured on the single-GPU replicas
+# that overshoots and the allocation dies with torch.OutOfMemoryError right
+# after the weights load (2.16 GiB requested, 116 MiB free). Do not "fix"
+# this into an empty expansion.
 : "${KV_MEM:=18563072000}"   # shipped kv-profiles.tsv row 2x7551-32624 @ 8/8192/262144/dflash
 : "${SPEC_METHOD:=dflash}"
 if [ "$SPEC_METHOD" = dflash ]; then : "${SPEC:=7}"; else : "${SPEC:=4}"; fi