#!/usr/bin/env bash
# Kimi-K3 TP=32 EP=32 benchmark experiment on 4x RTX 6000D (174.1.60.5~8).
# 固定单配置（TP32×EP32，跨 4 节点）；服务器生命周期走 deploy profile
# `pro6000/kimi3_pro6000_sglang_tp32ep32`（部署参数以 profile 为准，勿在此重复）。

EXPERIMENT="kimi3_pro6000_sglang_tp32ep32"
MODEL_NAME="Kimi-K3"
MODEL_PATH="/data/hf_models/Kimi-K3"
SERVED_MODEL_NAME="kimi-k3"

SGLANG_PORT="${SGLANG_PORT:-30000}"

# Python interpreter for orchestration scripts (parse_backend.py, compare.py, etc.)
# and the benchmark client. Defaults to the system python3 if the sglang venv
# does not exist on the host.
VENV_CLIENT="${VENV_CLIENT:-/root/.miniconda3/envs/sglang}"

# Run the benchmark client natively (0) or inside Docker (1).
USE_DOCKER_CLIENT="${USE_DOCKER_CLIENT:-1}"

export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,2,3,4,5,6,7}"

# Runtime working directory for logs, pid files, and tmp.
RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"

# 单配置：TP=32 DP=1（EP=32 与 RoCE 等参数固定在 deploy profile 内）
declare -a PARALLEL_CONFIGS=(
  "32 1"
)

# K3 服务器参数（与 deploy profile 保持一致，供本地/诊断脚本引用）。
MEM_FRACTION_STATIC="${MEM_FRACTION_STATIC:-0.88}"
MOE_RUNNER_BACKEND="${MOE_RUNNER_BACKEND:-marlin}"
EP_SIZE="${EP_SIZE:-32}"
MAX_RUNNING_REQUESTS="${MAX_RUNNING_REQUESTS:-64}"

# Deployment switch. 1 = Docker（走 deploy profile），0 = 本地 venv（仅单节点调试用）。
USE_DOCKER="${USE_DOCKER:-1}"
DOCKER_IMAGE="${DOCKER_IMAGE:-lmsysorg/sglang:kimi-k3}"

# Deploy profile used by start/stop scripts and the adaptive search loop.
DEPLOY_PROFILE="${DEPLOY_PROFILE:-pro6000/kimi3_pro6000_sglang_tp32ep32}"

# To use ShareGPT, set BENCH_DATASET_NAME=random and DATASET_PATH explicitly.
BENCH_DATASET_NAME="${BENCH_DATASET_NAME:-random}"
DATASET_PATH="${DATASET_PATH:-${ROOT_DIR}/dataset/ShareGPT_V3_unfiltered_cleaned_split.json}"
SGLANG_BENCH_MODULE="${SGLANG_BENCH_MODULE:-sglang.benchmark.serving}"

# Matrix and concurrency rules are defined in matrix.json by default.
MATRIX_FILE="${MATRIX_FILE:-${SCRIPT_DIR:-.}/matrix.json}"
MATRIX_MODE="${MATRIX_MODE:-Y}"

# Sampling density for concurrency.
export CONCURRENCY_SAMPLES="${CONCURRENCY_SAMPLES:-2}"

# Per-scenario timeout to avoid hangs (seconds). K3 首请求含 JIT 编译（~110s），
# 预热由 adaptive 框架处理；超时给足。
SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-3600}"

# GPU memory sampling interval (seconds).
GPU_MEM_SAMPLE_INTERVAL_S="${GPU_MEM_SAMPLE_INTERVAL_S:-1}"

# Dry-run mode: if 1, only log the server args and scenario plan without starting
# any server or sending requests.
DRY_RUN="${DRY_RUN:-0}"

# Per-config scenario limit for quick smoke tests. 0 = run all generated scenarios.
GRID_LIMIT="${GRID_LIMIT:-0}"

# PyTorch CUDA allocator setting for the SGLang server.
PYTORCH_CUDA_ALLOC_CONF="${PYTORCH_CUDA_ALLOC_CONF:-expandable_segments:True}"