#!/usr/bin/env bash
# Two NVFP4A16 quants, 2026-09-10. Operator: "run our own quant. w4a16 vllm
# servable, vision towers intact, mtp if applicable."
#   W4A16         -> --scheme NVFP4A16 (weight-only, NOT plain NVFP4/W4A4)
#   vision intact -> recipe ignore-list keeps vision/audio towers BF16
#   MTP           -> N/A: verified 0 mtp tensors in BOTH bf16 sources
# GPU1 not GPU0: the script onloads one layer at a time (GPU-light) but its own
# docstring warns of OOM when the card is not fairly free. GPU0 has 4.6 GiB spare
# (gen + mog-sec resident); GPU1 has ~19.3 GiB.
set -uo pipefail
WORK=/tank/aimodels/meromero-v2-nvfp4-work
CALIB=/tank/aimodels/heretic2-nvfp4-work/production_calib_512.jsonl
exec >> /home/infra-ops/quant/batch.log 2>&1

run_one () {
  local name="$1" src="$2" out="$3"
  echo "=== $(date -Is) START $name -> $out"
  docker rm -f meromero-quant >/dev/null 2>&1
  docker run --rm --name meromero-quant --gpus '"device=1"' --ipc host \
    -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \
    -v /tank/aimodels:/tank/aimodels \
    --entrypoint bash vllm/vllm-openai:latest -c "
      set -e
      pip install -q llmcompressor==0.13.0 tiktoken sentencepiece 2>&1 | tail -1
      python3 $WORK/quant_nvfp4_gemma.py \
        --model '$src' --calib '$CALIB' \
        --num-samples 512 --seqlen 8192 --scheme NVFP4A16 \
        --out '$out'
    "
  local rc=$?
  echo "=== $(date -Is) END $name rc=$rc size=$(du -sh "$out" 2>/dev/null | cut -f1)"
}

run_one A4B-heretic \
  /tank/aimodels/G4-MeroMero-26B-A4B-it-uncensored-heretic-bf16 \
  /tank/aimodels/G4-MeroMero-26B-A4B-it-uncensored-heretic-NVFP4A16
run_one v2-31B-heretic \
  /tank/aimodels/G4-MeroMero-v2-31B-heretic-bf16 \
  /tank/aimodels/G4-MeroMero-v2-31B-heretic-NVFP4A16
echo "=== $(date -Is) BATCH DONE"