feat: frank-default-large 2x 256k context slots (CTX_SIZE=524288, PARALLEL=2)

Total KV: ~12.8 GiB (6.4 GiB per slot × 2). Model is 98.5 GiB mmap'd
into 116 GiB SVM-backed unified memory.

scripts/frank-default-large.env

@@ -16,9 +16,10 @@
 # Q4_0_ROCMFP4_STRIX_LEAN quant, 98.5 GiB, 3-part GGUF split.
 # Text-only (no mmproj, no MTP draft head).
 #
-# Context: 131072 (128k) × 1 slot.  f16 KV cache.  --fit off because the
-# auto-fit code segfaults on this model's hyper-connection/indexer config;
-# -ngl 999 places all layers on the SVM-backed GPU pool (116 GiB unified).
+# Context: 262144 (256k) × 2 slots.  f16 KV cache (~6.4 GiB per slot,
+# ~12.8 GiB total).  --fit off because the auto-fit code segfaults on this
+# model's hyper-connection/indexer config; -ngl 999 places all layers on
+# the SVM-backed GPU pool (116 GiB unified).
 #
 # WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE. The
 # ROCm HIP runtime reads those bare env vars (see the 2026-08-13 TEMP
@@ -45,12 +46,12 @@ ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 
-# Serving: 131072 context (128k) × 1 slot. f16 KV, context checkpoints,
+# Serving: 262144 context (256k) × 2 slots. f16 KV, context checkpoints,
 # prompt cache. The model is 98.5 GiB loaded via mmap into the Strix Halo
 # unified memory pool (116 GiB SVM-backed). --fit off avoids the auto-fit
 # segfault on this model's qwen4exp hyper-connection/indexer configuration.
-CTX_SIZE=131072
-PARALLEL=1
+CTX_SIZE=524288
+PARALLEL=2
 BATCH_SIZE=4096
 UBATCH_SIZE=4096
 NUM_THREADS=16

scripts/serve-frank-large.sh

@@ -44,8 +44,8 @@ fi
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
-: "${CTX_SIZE:=131072}"
-: "${PARALLEL:=1}"
+: "${CTX_SIZE:=524288}"
+: "${PARALLEL:=2}"
 : "${BATCH_SIZE:=4096}"
 : "${UBATCH_SIZE:=4096}"
 : "${NUM_THREADS:=16}"