serverAppConfigs/scripts/download-frank-zealot-bonsai2-ptq1.sh

#!/usr/bin/env bash
# Candidate payload for frank-zealot: prism-ml/Ternary-Bonsai-2-27B-gguf at
# **PTQ1_0** — the DENSE ternary packing (1.75 bits/weight, 5.95 GB) of the same
# weights the live PQ2_0 endpoint serves (2.13 bits/weight, 7.21 GB). Public
# repo: no auth header, and never a token on the command line (a Bearer token is
# world-readable in /proc/<pid>/cmdline).
#
# WHY THIS ARM EXISTS. The whole argument is footprint: 5,946,648,928 B against
# the live 7,206,168,928 B = **1,201 MiB freed on the card**. On this endpoint
# KV bills 34,816 B/token (16 full-attention layers x 4 KV heads x 256 dim at
# q8_0 K + q8_0 V), so that one gap is ~37,000 tokens of pool per 1,201 MiB —
# context is exactly what the freed weight bytes buy.
#
# WHY IT MIGHT LOSE. The publisher's own throughput table (README, llama-bench,
# batch 1, depth 0): PTQ1_0 wins decode only on Ada/L4 (RTX 4090 91.1 vs 81.2,
# RTX 6000 Ada 90.4 vs 82.8, L4 32.1 vs 29.8) and LOSES on H100 (86.9 vs 113.9)
# and A100 (54.7 vs 73.9); prompt processing "favors PQ2_0 everywhere" (A100
# 706 vs 1328). The card text says explicitly that dense-trit unpacking costs
# arithmetic and the pack is "slower on Ampere, Hopper, and Blackwell". There is
# NO GA102/RTX 3090 row: the Ampere statement generalizes from an A100, which is
# instruction-bound at batch 1 with 2 TB/s of HBM, while the 3090 is the
# bandwidth-starved member of the family (936 GB/s) — the one regime where
# moving 17 % less weight per step can pay. That is an argument, not a
# measurement: this script exists so the decision is made on OUR card, against
# the PQ2_0 record (76.6 t/s single-stream decode, 1,258 t/s prefill at 35k).
# MEASURED ON OUR CARD (2026-10-18). Frank ordered this shape at 02:36 — Q8
# mmproj, batch 3072/ubatch 1536, two contexts — and the unit ran it as
# production 03:14:39→03:38:57 (pid 191358, journal `type ptq1_0: 402 tensors`).
# Its own print_timing lines: decode **48.0 / 47.6 t/s at 512 tokens** (47.9 at
# 229, 49.0 at 451), 25–27 t/s per stream with two streams live, prefill 1,295
# t/s at 30,637 → 943 at 97,856 → 801 at 141,365. The 1,201 MiB arrived and the
# decode tax came with it: −37 % against the PQ2_0 record, so the Ampere warning
# DOES generalize to GA102. Frank scratched the 27B plan at 03:33 for the 9B;
# this payload is the 27B rollback, not a candidate.
#
# THE RUNTIME LOCK CARRIES OVER. Both packings are custom GGML tensor types and
# stock llama.cpp rejects them ("It rejects PQ2_0 and PTQ1_0 as unknown types"
# — the card), so the PrismML fork build stays mandatory. Confirm the loadability
# against the installed binary BEFORE pointing any unit at this file.
#
# The vision projector is the SAME file the PQ2_0 endpoint already uses (Hub LFS
# oid 6807ede61d57… matches byte-for-byte), so it is HARDLINKED from the existing
# payload dir instead of re-downloaded — a hardlink is a regular file, so the
# serve gates' no-symlink rule stays satisfied.
#
# Usage:
#   scripts/download-frank-zealot-bonsai2-ptq1.sh [DEST_DIR] [--verify-only]
set -euo pipefail

DEST=""
VERIFY_ONLY=0
for arg in "$@"; do
    case "$arg" in
        --verify-only) VERIFY_ONLY=1 ;;
        *) DEST="$arg" ;;
    esac
done
DEST="${DEST:-/home/dank/models/Bonsai2-PTQ1_0}"
LINK_SRC="${LINK_SRC:-/home/dank/models/Bonsai2-PQ2_0}"

REPO="prism-ml/Ternary-Bonsai-2-27B-gguf"
MMPROJ="Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf"
MMPROJ_SIZE=629246976
MMPROJ_SHA="6807ede61d570bb86ba34b756a0fa109edc33668604de867c6ea6d8f1d631903"

# hub-name | dest-name | bytes | sha256 (Hub LFS oid)
FILES=(
  "Ternary-Bonsai-2-27B-PTQ1_0.gguf|Ternary-Bonsai-2-27B-PTQ1_0.gguf|5946648928|53107f530aa52eb00912263ab1ee29bd199261c87cd7b4ad4ca1318c1fe33ee3"
)

mkdir -p "$DEST"
status=0

check() { # file size sha -> 0 when byte- and hash-exact
    [[ -f "$1" ]] && [[ "$(stat -c%s "$1")" == "$2" ]] \
        && sha256sum -c --quiet <(printf '%s  %s\n' "$3" "$1")
}

for entry in "${FILES[@]}"; do
  IFS='|' read -r hubname destname size sha <<<"$entry"
  f="$DEST/$destname"
  if check "$f" "$size" "$sha"; then
    echo "OK        $destname"
    continue
  fi
  if (( VERIFY_ONLY )); then
    echo "MISSING   $destname"
    status=1
    continue
  fi
  echo "FETCHING  $destname (from $REPO)"
  tmp="$f.part"
  # No resume: `curl -C -` once produced an oversized file on a 31 GiB payload.
  # -f/--fail-with-body so an HTTP 401/403 body is never written as success.
  curl -fsSL --fail-with-body --retry 3 --retry-delay 5 \
      -o "$tmp" "https://huggingface.co/${REPO}/resolve/main/${hubname}"
  mv "$tmp" "$f"
  if ! check "$f" "$size" "$sha"; then
    echo "FAIL      $destname (size $(stat -c%s "$f" 2>/dev/null || echo none) != $size, or sha mismatch)"
    status=1
    continue
  fi
  echo "VERIFIED  $destname"
done

# Vision projector: hardlink the identical file when a verified copy exists.
mm="$DEST/$MMPROJ"
if check "$mm" "$MMPROJ_SIZE" "$MMPROJ_SHA"; then
  echo "OK        $MMPROJ"
elif [[ -f "$LINK_SRC/$MMPROJ" ]] && check "$LINK_SRC/$MMPROJ" "$MMPROJ_SIZE" "$MMPROJ_SHA"; then
  ln "$LINK_SRC/$MMPROJ" "$mm" && echo "HARDLINKED $MMPROJ from $LINK_SRC"
elif (( VERIFY_ONLY )); then
  echo "MISSING   $MMPROJ"
  status=1
else
  echo "FETCHING  $MMPROJ (no verified source copy to link)"
  curl -fsSL --fail-with-body --retry 3 --retry-delay 5 \
      -o "$mm.part" "https://huggingface.co/${REPO}/resolve/main/${MMPROJ}"
  mv "$mm.part" "$mm"
  if ! check "$mm" "$MMPROJ_SIZE" "$MMPROJ_SHA"; then
    echo "FAIL      $MMPROJ"
    status=1
  else
    echo "VERIFIED  $MMPROJ"
  fi
fi

if (( status == 0 )); then
  echo "DOWNLOAD_DONE $DEST"
else
  echo "DOWNLOAD_FAILED $DEST" >&2
fi
exit "$status"