frank-large: mmap the CPU-overridden weights (no CUDA_Host pinning)

scripts/frank-large.service

@@ -7,6 +7,11 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
+# Staging buffers for the CUDA transfers are page-locked; the weights
+# themselves stay mmapped (GGML_CUDA_NO_PINNED_WEIGHTS=1), but the staging
+# budget still needs room. Parity with the halogen quadlet's
+# Ulimit=memlock=-1:-1.
+LimitMEMLOCK=infinity
 Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env"
 ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
 Restart=on-failure