looping..
#7
by remaxx - opened
I tryd to use it on my hermes agent but keep going in loop after thinking i guess for long time im using DGX Spark.
remaxx changed discussion title from loop. to looping..
If you disable DFlash and use sglang image with tag dev-cu13 (released on 30.06.2026) - it works perfectly. My settings to try/run it on 1 B200 are:
sglang serve
--model-path /models/Laguna-S-2.1-NVFP4
--served-model-name Laguna-S-2.1
--host 0.0.0.0
--port 8000
--allow-auto-truncate
--attention-backend trtllm_mha
--mm-attention-backend fa4
--disable-overlap-schedule
--mem-fraction-static 0.8
--cuda-graph-max-bs-decode 32
--max-running-requests 32
--context-length 175000
--tool-call-parser poolside_v1
--reasoning-parser poolside_v1
--chunked-prefill-size 8192
--trust-remote-code
--enable-metrics