vh
f44280e6b2
Image local/mia:0.1.0 built from stacks/mia: MIA v2 @ bbd8b158 (MIT) with its pinned submodules, dread-dev's proven Python lock with the torch family swapped to cu129, and a driver adapted from dread-dev's run_mia.py that seeds every mesh (fix_random + trimesh's module RNG) and writes weights_effective into the npz. Weights stay in fv-ml1's shared HF cache at pinned revisions, mounted read-only. scripts/mia-run mirrors blender-run: --job DIR is shipped to fv-ml1:/tank/mia/jobs, one docker run --rm rigs every mesh, out/ comes back. Acceptance on the four Dread Naught characters: 3.9-4.7 s a mesh (median of 3) plus 12.7 s model load, peak 3,394 MiB; seeded runs bit-identical across rotated mesh order; GPU-vs-CPU distances the same size as sampling noise, with an unseeded GPU run as the positive control.
86 lines
4.8 KiB
Bash
Executable File
86 lines
4.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# mia-run — one-shot Make-It-Animatable v2 auto-rig on fv-ml1 GPU 3 (dread-dev / Dread Naught;
|
|
# Prime's request, 2026-10-01). Same shape as blender-run: a container starts, rigs, exits, and
|
|
# hands the GPU back. NOT a seat; nothing stays up between calls.
|
|
#
|
|
# scripts/mia-run --job DIR [--seed N | --unseeded] -- <name>=<input.glb> [<name>=<input.glb> ...]
|
|
# scripts/mia-run --job ~/development/dreadnaught/rig-jobs/j1 -- goblin=in/goblin.glb ogre=in/ogre.glb
|
|
#
|
|
# Inputs are paths RELATIVE TO DIR and must be inside it: DIR is the only thing shipped to fv-ml1.
|
|
# Per mesh, DIR/out/ receives:
|
|
# <name>_pred.npz predictions in the input's coordinates, WITH `weights_effective`
|
|
# (the finalize.py formula), so no finalize step is needed afterwards
|
|
# <name>.fbx .glb _rest.glb MIA's own exports (UI defaults, static rig)
|
|
# <name>_apose-hint.fbx .glb _rest.glb same predictions, Blender stage with the A-pose hint
|
|
# <name>_run.json stage timings, model-load time, peak GPU memory, seed, provenance
|
|
# The model load (~3 x 1 GB checkpoints) is paid once per call, so pass every mesh in one call.
|
|
#
|
|
# SEEDED BY DEFAULT (seed 0): before every mesh the driver calls MIA's fix_random(seed) and resets
|
|
# trimesh's module RNG, which fix_random never reaches (trimesh >= 4 samples surfaces from
|
|
# trimesh.util._RANDOM_DEFAULT). Without that, runs of the same mesh differ: joints by 0.1-0.27% of
|
|
# height on dread-dev's CPU noise floor. --unseeded restores upstream behaviour.
|
|
#
|
|
# Files: fv-ml1 does NOT mount /mnt/smithy. DIR is mirrored to
|
|
# fv-ml1:/tank/mia/jobs/<basename>-<hash of DIR's absolute path>/ (rsync --delete, so a rerun never
|
|
# inherits leftovers), the driver runs WITH THAT AS ITS WORKING DIRECTORY, and new or changed files
|
|
# are copied back into DIR afterwards (nothing is ever deleted locally). Running the SAME DIR twice
|
|
# concurrently shares one remote dir, so don't. Remote job dirs are never swept.
|
|
#
|
|
# Image: local/mia (stacks/mia; IMAGE= in fv-ml1:/opt/docker/compose/mia/.env). Weights come from
|
|
# the read-only /tank/aimodels/huggingface mount at pinned revisions; the run never touches the
|
|
# network (HF_HUB_OFFLINE=1). The skeleton template is a SUBSTITUTE ("Standard Run.fbx"): the
|
|
# official one is in a gated HF dataset whose terms were not accepted (see stacks/mia/README.md).
|
|
#
|
|
# Budget: GPU 3 (96 GB, borrowed from the vLLM reserve, shared on demand with Blender and Scriberr;
|
|
# this ends if a full-size seat moves in). Capped at 32 GB RAM / 16 CPUs so a runaway mesh cannot
|
|
# starve the inference seats on the same host.
|
|
set -euo pipefail
|
|
|
|
HOST=${MIA_SSH_HOST:-infra-ops@10.251.50.54}
|
|
ENV_FILE=/opt/docker/compose/mia/.env
|
|
JOB=""
|
|
DRIVER_OPTS=()
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
--job) JOB=${2:?--job needs a directory}; shift 2 ;;
|
|
--seed) DRIVER_OPTS+=(--seed "${2:?--seed needs an integer}"); shift 2 ;;
|
|
--unseeded) DRIVER_OPTS+=(--unseeded); shift ;;
|
|
--) shift; break ;;
|
|
-h|--help) sed -n 2,40p "$0"; exit 0 ;;
|
|
*) echo "mia-run: unknown option $1 (meshes go after --)" >&2; exit 2 ;;
|
|
esac
|
|
done
|
|
[ -n "$JOB" ] || { echo "mia-run: --job DIR is required (inputs are read from it, out/ is written into it)" >&2; exit 2; }
|
|
[ $# -gt 0 ] || { echo "mia-run: no meshes; pass <name>=<input.glb> after --" >&2; exit 2; }
|
|
[ -d "$JOB" ] || { echo "mia-run: --job $JOB is not a directory" >&2; exit 2; }
|
|
ABS=$(realpath "$JOB")
|
|
BASE=$(basename "$ABS")
|
|
[[ $BASE =~ ^[A-Za-z0-9._-]+$ ]] || { echo "mia-run: job dir name '$BASE' must be [A-Za-z0-9._-]" >&2; exit 2; }
|
|
for m in "$@"; do
|
|
[[ $m == *=* ]] || { echo "mia-run: '$m' is not <name>=<input.glb>" >&2; exit 2; }
|
|
f=$(realpath -m "$ABS/${m#*=}")
|
|
[[ $f == "$ABS"/* && -f $f ]] || { echo "mia-run: input '${m#*=}' is not a file inside $ABS" >&2; exit 2; }
|
|
done
|
|
|
|
# Keyed on basename + a hash of the ABSOLUTE local path, as blender-run: two dirs that share a
|
|
# basename never share a remote dir. rsync removes only inside that one remote dir; there is no rm
|
|
# on a computed path.
|
|
NAME=$BASE-$(printf '%s' "$ABS" | sha256sum | cut -c1-8)
|
|
ssh -n -o BatchMode=yes "$HOST" "mkdir -p /tank/mia/jobs/$NAME"
|
|
rsync -a --delete "$JOB"/ "$HOST:/tank/mia/jobs/$NAME/"
|
|
|
|
# Arguments travel as one shell-quoted string: ssh flattens argv into a remote command line.
|
|
ARGS=$(printf '%q ' "${DRIVER_OPTS[@]}" "$@")
|
|
set +e
|
|
ssh -n -o BatchMode=yes "$HOST" "IMG=\$(grep '^IMAGE=' $ENV_FILE | cut -d= -f2) && \
|
|
exec docker run --rm --name mia-run-\$\$ --hostname fv-ml1-mia \
|
|
--runtime nvidia -e NVIDIA_VISIBLE_DEVICES=3 -e NVIDIA_DRIVER_CAPABILITIES=compute,utility \
|
|
--user 1002:1003 --memory 32g --cpus 16 \
|
|
--mount type=bind,src=/tank/aimodels/huggingface,dst=/hf,readonly \
|
|
--mount type=bind,src=/tank/mia/jobs/$NAME,dst=/job \
|
|
-w /job \"\$IMG\" $ARGS"
|
|
RC=$?
|
|
set -e
|
|
rsync -a --update "$HOST:/tank/mia/jobs/$NAME/" "$JOB"/
|
|
exit $RC
|