#!/usr/bin/env bash

set -euo pipefail

OUTPUT_ROOT="${OUTPUT_ROOT:?OUTPUT_ROOT must be set}"
RUN_DIR="$(pwd -P)"
PROFILE_DIR="${PROFILE_DIR:-${RUN_DIR%/runs/frontier-fidelity-envelope-v1}/runs/frontier-qwen30-vllm020-profile-v1}"
VENV_ROOT="${VENV_ROOT:-/tmp/wjh/venvs/vllm-0.20.0-cu129-profiler-v1}"
PROFILE_HOME="${PROFILE_HOME:-/tmp/wjh}"
VLLM_SOURCE="${VLLM_SOURCE:-/home/admin/cpfs/wjh/agentic-kv/third_party/vllm_v20_build}"
FRONTIER_SOURCE="${FRONTIER_SOURCE:-/home/admin/cpfs/wjh/aituner/frontier-t1-dash0-deadc4a}"
MODEL_ROOT="${MODEL_ROOT:-/home/admin/cpfs/wjh/models/Qwen/Qwen3-30B-A3B}"
TOKENS="${TOKENS:-1 2 4 8 16 24 32 40 48 56 64 72 80 88 96 104 112 120 128}"
export HOME="${PROFILE_HOME}"
export XDG_CACHE_HOME="${PROFILE_HOME}/.cache"
export VLLM_CACHE_ROOT="${XDG_CACHE_HOME}/vllm"

mkdir -p "${OUTPUT_ROOT}/logs" "${OUTPUT_ROOT}/provenance" "${OUTPUT_ROOT}/raw"
exec > >(tee -a "${OUTPUT_ROOT}/logs/moe-router.log") 2>&1
IFS=',' read -r -a GPU_IDS <<< "${CUDA_VISIBLE_DEVICES:?a fleet-allocated GPU is required}"
if [[ "${#GPU_IDS[@]}" -ne 1 ]]; then
  echo "expected exactly one GPU, got ${CUDA_VISIBLE_DEVICES}" >&2
  exit 1
fi

echo "PROFILE_LAUNCH_ECHO host=$(hostname) gpu=${CUDA_VISIBLE_DEVICES} role=MoE+router-kernel-only tp=1,2,4 tokens='${TOKENS}' method=Frontier-RecordFunctionTracer output=${OUTPUT_ROOT} expected_wall=10-30m expected_gpu_cap=1.0_H20h"
date -u +"START_UTC=%Y-%m-%dT%H:%M:%SZ"
test "$(git -C "${FRONTIER_SOURCE}" rev-parse HEAD)" = "deadc4a321f0baaa534c6ebd17f974123733cdc2"
test "$(git -C "${VLLM_SOURCE}" rev-parse HEAD)" = "88d34c6409e9fb3c7b8ca0c04756f061d2099eb1"
git rev-parse HEAD > "${OUTPUT_ROOT}/provenance/aituner.commit"
git -C "${FRONTIER_SOURCE}" rev-parse HEAD > "${OUTPUT_ROOT}/provenance/frontier.commit"
printf '%s\n' ${TOKENS} > "${OUTPUT_ROOT}/provenance/tokens.txt"
sha256sum "${PROFILE_DIR}/profile_vllm020_moe.py" "${PROFILE_DIR}/profile_vllm020_router.py" "${RUN_DIR}/run_graph_kernel_only_moe.sh" > "${OUTPUT_ROOT}/provenance/source.sha256"

timeout --signal=TERM --kill-after=30s 2400 \
  "${VENV_ROOT}/bin/python" "${PROFILE_DIR}/profile_vllm020_moe.py" \
  --vllm-source "${VLLM_SOURCE}" --frontier-source "${FRONTIER_SOURCE}" \
  --model "${MODEL_ROOT}" --output "${OUTPUT_ROOT}/raw/moe.json" \
  --tp 1 2 4 --num-tokens ${TOKENS} --routing-modes uniform_random_logits \
  --warmup-iters 3 --repeats 5 --profile-method record_function --check-reference

timeout --signal=TERM --kill-after=30s 1800 \
  "${VENV_ROOT}/bin/python" "${PROFILE_DIR}/profile_vllm020_router.py" \
  --vllm-source "${VLLM_SOURCE}" --frontier-source "${FRONTIER_SOURCE}" \
  --model "${MODEL_ROOT}" --output "${OUTPUT_ROOT}/raw/router.json" \
  --num-tokens ${TOKENS} --warmup-iters 3 --repeats 5 --profile-method record_function

test -s "${OUTPUT_ROOT}/raw/moe.json"
test -s "${OUTPUT_ROOT}/raw/router.json"
sha256sum "${OUTPUT_ROOT}/raw"/*.json "${OUTPUT_ROOT}/provenance"/* > "${OUTPUT_ROOT}/artifacts.sha256"
date -u +"END_UTC=%Y-%m-%dT%H:%M:%SZ"
echo "GRAPH_KERNEL_ONLY_MOE_COMPLETE"