#!/bin/bash
# Run the Heretic2 NVFP4 production quant on ana-ml2 GPU0 (freed for the window).
# llmcompressor + tokenizer deps pip-installed into a vLLM container (torch/CUDA ready).
set -euo pipefail
WORK=/tank/aimodels/heretic2-nvfp4-work
MODE="${1:-chat}"                       # chat = production 512-row mix; text = AEON baseline
CALIB="${2:-$WORK/production_calib_512.jsonl}"
OUT="${3:-$WORK/heretic2-mtp-nvfp4-prod}"

docker run --rm --gpus '"device=0"' --ipc host \
  -v /tank/aimodels:/tank/aimodels \
  --entrypoint bash vllm/vllm-openai:v0.24.0 -c "
    set -e
    pip install -q llmcompressor tiktoken sentencepiece 2>&1 | tail -1
    python3 $WORK/quant_nvfp4.py \
      --model $WORK/heretic2-mtp-bf16 \
      --calib-mode $MODE --calib $CALIB \
      --num-samples 512 --seqlen 8192 \
      --out $OUT
  "