Files
localgenai/pyinfra/framework/scripts/swap-model

187 lines
6.6 KiB
Bash
Executable File

#!/usr/bin/env bash
# swap-model — coordinate which inference container is GPU-resident on
# the Strix Halo box.
#
# Why this exists. The GPU's merged ~110 GB arena (BIOS UMA=0.5 GB +
# ttm.pages_limit + HSA_XNACK; see StrixHaloMemory.md) holds at most
# one 88 GB-class model at a time, and ROCm doesn't reclaim cleanly
# between consumers. So switching models means stop-then-start of
# whole compose stacks. This script encodes the per-target conflict
# table + per-service health probes so the swap is one command.
#
# Usage:
# swap-model coder # Qwen3-Coder-30B via Ollama (interactive)
# swap-model 235b # Qwen3-235B-A22B via llama.cpp (long-task)
# swap-model kimi # Kimi-Linear-48B-A3B via vLLM (long-context)
# swap-model qwable # Qwable-3.6-27B via llama.cpp (Fable-style)
# swap-model comfyui # ComfyUI (image generation)
# swap-model none # everything down — free the GPU
# swap-model status # show what's currently up
#
# Env knobs:
# SWAP_WAIT_TIMEOUT seconds to wait for /health after up; default 600
# (235B's 88 GB cold load can take 3-5 min)
#
# Out of scope (deliberately):
# - Always-on services (openwebui, litellm, phoenix, beszel, etc.) —
# no GPU footprint, left alone.
# - llama.cpp 30B (port 8080) — same weights as Ollama's qwen3-coder
# but still LL-P0 perf-evaluating. `coder` target uses Ollama only.
# - Multi-target combos (e.g. kimi+ollama coexist on the arena);
# for now run swap-model twice if you want both.
set -euo pipefail
COMPOSE_ROOT="/srv/docker"
WAIT_TIMEOUT="${SWAP_WAIT_TIMEOUT:-600}"
# --- Service table -----------------------------------------------------------
# Map short name → compose dir (under $COMPOSE_ROOT) and health URL.
# Container name == compose dir name in every case (intentional convention,
# enforced in compose/*.yml's container_name fields).
declare -A SVC_DIR=(
[ollama]=ollama
[llama]=llama
[kimi]=kimi-linear
[235b]=qwen3-235b
[qwable]=qwable
[comfyui]=comfyui
)
declare -A SVC_HEALTH=(
[ollama]="http://127.0.0.1:11434/api/tags"
[llama]="http://127.0.0.1:8080/health"
[kimi]="http://127.0.0.1:8000/v1/models"
[235b]="http://127.0.0.1:8081/health"
[qwable]="http://127.0.0.1:8082/health"
[comfyui]="http://127.0.0.1:8188/"
)
# --- Target → plan -----------------------------------------------------------
# UP = services that should be running after the swap
# DOWN = services that must be stopped to free the GPU arena
# (anything not in either list is left untouched — e.g. switching to coder
# leaves kimi alone, since kimi(30 GB) + ollama(30 GB) fit in the arena.)
plan() {
UP=() ; DOWN=()
case "$1" in
coder) UP=(ollama) ; DOWN=(235b comfyui) ;;
235b) UP=(235b) ; DOWN=(ollama llama kimi qwable comfyui) ;;
kimi) UP=(kimi) ; DOWN=(235b comfyui) ;;
qwable) UP=(qwable) ; DOWN=(235b comfyui) ;;
comfyui) UP=(comfyui) ; DOWN=(235b kimi qwable) ;;
none) UP=() ; DOWN=(ollama llama kimi 235b qwable comfyui) ;;
*) return 1 ;;
esac
}
# --- Probes ------------------------------------------------------------------
is_running() {
docker inspect -f '{{.State.Running}}' "$1" 2>/dev/null | grep -q true
}
is_healthy() {
curl -fsS --max-time 5 "$1" >/dev/null 2>&1
}
wait_healthy() {
local svc="$1" url="${SVC_HEALTH[$1]}" deadline=$(( SECONDS + WAIT_TIMEOUT ))
printf " waiting for %s health (timeout %ss)" "$svc" "$WAIT_TIMEOUT"
while ! is_healthy "$url"; do
if (( SECONDS > deadline )); then
printf " TIMEOUT\n"
echo " last 20 lines of container log:" >&2
docker logs --tail 20 "${SVC_DIR[$svc]}" 2>&1 | sed 's/^/ /' >&2
return 1
fi
sleep 5
printf "."
done
printf " ok\n"
}
# --- Actions -----------------------------------------------------------------
down_svc() {
local svc="$1" dir="$COMPOSE_ROOT/${SVC_DIR[$1]}"
if ! is_running "${SVC_DIR[$svc]}"; then
echo " $svc: already down"
return 0
fi
echo " stopping $svc"
(cd "$dir" && docker compose down)
}
up_svc() {
local svc="$1" dir="$COMPOSE_ROOT/${SVC_DIR[$1]}"
if is_running "${SVC_DIR[$svc]}" && is_healthy "${SVC_HEALTH[$svc]}"; then
echo " $svc: already up + healthy"
return 0
fi
if [[ ! -d "$dir" ]]; then
echo " $svc: compose dir $dir missing — run pyinfra deploy first" >&2
return 1
fi
echo " starting $svc"
(cd "$dir" && docker compose up -d)
wait_healthy "$svc"
}
show_status() {
echo "Inference services:"
for svc in ollama llama kimi 235b qwable comfyui; do
local container="${SVC_DIR[$svc]}" state="down" health=""
if is_running "$container"; then
state="up"
if is_healthy "${SVC_HEALTH[$svc]}"; then
health=" (healthy)"
else
health=" (starting/unhealthy)"
fi
fi
printf " %-8s %s%s\n" "$svc" "$state" "$health"
done
}
usage() {
cat <<EOF
swap-model — coordinate inference containers on Strix Halo.
Usage:
swap-model coder # Qwen3-Coder-30B (Ollama, interactive daily-driver)
swap-model 235b # Qwen3-235B-A22B (llama.cpp, long-task, ~5-10 tok/s)
swap-model kimi # Kimi-Linear-48B (vLLM, long-context chat)
swap-model qwable # Qwable-3.6-27B (llama.cpp, Fable-style, ~10-15 tok/s)
swap-model comfyui # ComfyUI (image generation)
swap-model none # everything down (free the GPU arena)
swap-model status # show current state
Behaviour: stops conflicting services (frees the 110 GB GPU arena),
starts the target, polls its /health until it returns 200. Wait timeout
defaults to ${WAIT_TIMEOUT}s; override with SWAP_WAIT_TIMEOUT.
Coexistence: ollama(30B), kimi, and qwable(27B, 16.5 GB) coexist with
each other. 235B and comfyui coexist with nothing. See
compose/qwen3-235b/README.md for arena math.
EOF
}
# --- Main --------------------------------------------------------------------
TARGET="${1:-}"
case "$TARGET" in
coder|235b|kimi|qwable|comfyui|none) ;;
status) show_status ; exit 0 ;;
-h|--help|help|"") usage ; exit 0 ;;
*)
echo "swap-model: unknown target '$TARGET'" >&2
echo "Try: swap-model help" >&2
exit 2
;;
esac
plan "$TARGET"
echo "Plan: down=[${DOWN[*]:-}] up=[${UP[*]:-}]"
for svc in "${DOWN[@]}"; do down_svc "$svc"; done
for svc in "${UP[@]}"; do up_svc "$svc"; done
echo
show_status