promote NPU endpoint to frank-default-small: FLM serve unit + wrapper + env (gemma4-it:e4b default), LimitMEMLOCK=infinity (2026-08-16)

This commit is contained in:
Frank committed 2026-08-16 14:19:37 -07:00
1 parent 48142f5d8e
commit f6737f234d
3 files changed
+65 -63

No files matched your search

+7 -4
View File
@@ -1,14 +1,17 @@
[Unit]
Description=llama.cpp DFlash inference (frank-default-small)
After=network.target
Description=FastFlowLM NPU inference (frank-default-small) on Dankclaw
After=network-online.target
Wants=network-online.target
[Service]
Type=simple
User=dank
Group=dank
ExecStart=/home/dank/vLLM/scripts/serve-llama-frank-small.sh
Environment="FLM_SMALL_ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-small.env"
ExecStart=/home/dank/vllmScripts/scripts/serve-flm-small.sh
LimitMEMLOCK=infinity
Restart=on-failure
RestartSec=10
[Install]
WantedBy=multi-user.target
WantedBy=multi-user.target