frank-default-large: cap CTX_SIZE at 131072 — 262144 OOMs SVM pool (cudaMalloc 103176 MiB failed with fully GPU-resident 87 GiB model)

scripts/frank-default-large.env

@@ -54,12 +54,17 @@ ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 
-# Serving: 262144-token context on ONE slot (parallel 1), batch 4096 /
+# Serving: 131072-token context on ONE slot (parallel 1), batch 4096 /
 # ubatch 4096, 16+16 threads, f16 KV, 16 context checkpoints, 8 GiB
 # prompt cache. --fit off: auto-fit segfaults on this model's
 # hyper-connection/indexer config; -ngl 999 puts every layer on the
 # SVM-backed GPU pool.
-CTX_SIZE=262144
+#
+# CTX_SIZE is capped at 131072: the fully GPU-resident 87 GiB model plus a
+# 262144-token f16 KV cache and the worst-case compute buffer exceed the
+# Strix Halo SVM pool — verified live (cudaMalloc 103176 MiB OOM at
+# 262144). 131072 is the proven STRIX-family value on this box.
+CTX_SIZE=131072
 PARALLEL=1
 BATCH_SIZE=4096
 UBATCH_SIZE=4096

scripts/serve-frank-large.sh

@@ -45,7 +45,7 @@ fi
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
-: "${CTX_SIZE:=262144}"
+: "${CTX_SIZE:=131072}"
 : "${PARALLEL:=1}"
 : "${BATCH_SIZE:=4096}"
 : "${UBATCH_SIZE:=4096}"