Swap fleet naming + restore Qwen3.6-35B-A3B Q6_K_P on Dankserver

- Restore the pre-2026-08-17 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
  Q6_K_P + ngram-mod setup as frank-default-small on Dankserver (port 7770,
  upstream llama.cpp b10121, MoE experts on CPU via --n-cpu-moe 36).
- Rename the CIRU Qwen3.8-27B ActiveFPX setup from frank-default-small to
  frank-default-large (Dankclaw, port 52625); bump to CTX_SIZE=262144
  (native max) and PARALLEL=2 (96 GiB unified pool).
- Retire the Qwen3.8-27B IQ4_XS FastMTP frank-default-large (Dankserver) to
  .AGENTTRASH.
- deploy.sh: SERVICE[dankserver]=frank-default-small,
  SERVICE[dankclaw]=frank-default-large; HEALTH_WAIT[dankserver]=600.
This commit is contained in:
Frank
2026-08-18 00:32:26 -07:00
parent fe1d834d37
commit 1ba9618fcc
7 changed files with 262 additions and 276 deletions
+7 -6
View File
@@ -17,8 +17,8 @@
# FRANK_SUDO_PW=... ./deploy.sh <target>
#
# Targets (2026-08-18 topology):
# dankserver - llama.cpp FastMTP (frank-default-large.service, port 7770)
# dankclaw - CIRU ROCmFPX llama.cpp (frank-default-small.service, port 52625)
# dankserver - llama.cpp Qwen3.6-35B-A3B Q6_K_P (frank-default-small.service, port 7770)
# dankclaw - CIRU ROCmFPX llama.cpp Qwen3.8-27B (frank-default-large.service, port 52625)
set -euo pipefail
# ---------------------------------------------------------------------------
@@ -29,16 +29,17 @@ declare -A REMOTE_USER REMOTE_HOST REMOTE_DIR SERVICE SERVICE_HEALTH DROP_CACHES
REMOTE_USER[dankserver]=dank
REMOTE_HOST[dankserver]=dankserver
REMOTE_DIR[dankserver]="/home/dank/vLLM"
SERVICE[dankserver]="frank-default-large"
SERVICE[dankserver]="frank-default-small"
SERVICE_HEALTH[dankserver]="http://127.0.0.1:7770/health"
DROP_CACHES[dankserver]=0
# Cold load: --no-mmap reads 15.7 GB through RAM; allow 10 minutes.
HEALTH_WAIT[dankserver]=300
# Cold load: --no-mmap reads the 30.6 GB Q6_K_P through RAM (MoE experts on
# CPU); allow 20 minutes.
HEALTH_WAIT[dankserver]=600
REMOTE_USER[dankclaw]=dank
REMOTE_HOST[dankclaw]=dankclaw
REMOTE_DIR[dankclaw]="/home/dank/vllmScripts"
SERVICE[dankclaw]="frank-default-small"
SERVICE[dankclaw]="frank-default-large"
SERVICE_HEALTH[dankclaw]="http://127.0.0.1:52625/health"
DROP_CACHES[dankclaw]=0
# CIRU llama.cpp (ROCm 7.15) loads the 34.9 GiB ActiveFPX payload + MTP