#!/bin/bash
# Serve the NVFP4+MTP Heretic2 seat on ana-ml2 GPU0 for P00 validation.
# vLLM compressed-tensors NVFP4 + qwen3_5_mtp spec-decode (pantheon pattern).
# Served as char-rp-reasoning on :8018 (the GGUF seat's port; that seat is stopped).
set -euo pipefail
WORK=/tank/aimodels/heretic2-nvfp4-work
docker rm -f vllm-charrp-nvfp4-test 2>/dev/null || true

docker run -d --name vllm-charrp-nvfp4-test --gpus '"device=0"' --ipc host \
  -v /tank/aimodels:/tank/aimodels -p 8018:8000 \
  vllm/vllm-openai:v0.24.0 \
  "$WORK/heretic2-mtp-nvfp4-prod" \
  --quantization compressed-tensors \
  --speculative-config '{"method":"qwen3_5_mtp","num_speculative_tokens":3}' \
  --reasoning-parser qwen3 --tool-call-parser qwen3_coder --enable-auto-tool-choice \
  --language-model-only \
  --mamba-cache-dtype float32 \
  --served-model-name char-rp-reasoning \
  --max-model-len 40960 --max-num-seqs 256 --gpu-memory-utilization 0.45 --trust-remote-code
echo "container started: $(docker ps --filter name=vllm-charrp-nvfp4-test --format '{{.Status}}')"