# TP×DP matrix experiment for DeepSeek-V4-Flash on Ascend 910C (8 NPUs / 16 dies)
# using vLLM-Ascend.
# Tests vLLM with three parallel configurations:
#   TP=2, DP=4  -> 2 dies per replica, 4 replicas
#   TP=4, DP=2  -> 4 dies per replica, 2 replicas
#   TP=8, DP=1  -> 8 dies, no data parallelism
#
# Platform: ascend_910c (see platforms/ascend_910c.env).
# Host: 910c.1 / NPU-NODE61, openEuler 22.03 SP4 aarch64, driver 25.5.2, CANN 9.0.0.
#
# ⚠️ PLACEHOLDER: DeepSeek-V4-Flash weights are NOT yet present on this host
#   (only GLM-5.2-{w4a8c8,w8a8} under /mnt/models). Download DSV4-Flash first,
#   then fix MODEL_PATH below. Smoke run will fail until the model exists.
#   Recommended host path: /mnt/models/DeepSeek-V4-Flash  (FP8)
#                          /mnt/models/DeepSeek-V4-Flash-INT8 (INT8)

EXPERIMENT="dsv4_910c_vllm_tp_dp_matrix"
MODEL_NAME="DeepSeek-V4-Flash"
# TODO: point this at the real DSV4-Flash directory once downloaded.
MODEL_PATH="${MODEL_PATH:-/mnt/models/DeepSeek-V4-Flash}"
SERVED_MODEL_NAME="deepseek-v4-flash"

VLLM_PORT="${VLLM_PORT:-30052}"

# Dedicated container name so this experiment never touches other 910c runs.
CONTAINER_NAME="${CONTAINER_NAME:-vllm-ascend-dsv4-910c}"

# Python interpreter for the benchmark client inside the vllm-ascend container.
CONTAINER_PYTHON="${CONTAINER_PYTHON:-/usr/local/bin/python}"

# vllm-ascend image. Use the general v0.23 image for DSV4 (the GLM5.2-tuned
# variant may carry GLM-specific patches). Load from:
#   /mnt/models/vllm-ascend-v0.23.0rc1-a3-openeuler.tar
USE_DOCKER="${USE_DOCKER:-1}"
DOCKER_IMAGE="${DOCKER_IMAGE:-vllm-ascend:v0.23.0rc1-a3-openeuler}"

DOCKER_CLIENT_IMAGE="${DOCKER_CLIENT_IMAGE:-lmsysorg/sglang:latest}"
USE_DOCKER_CLIENT="${USE_DOCKER_CLIENT:-0}"

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

RUNTIME_BASE="${RUNTIME_BASE:-${SCRIPT_DIR}/runtime}"

# Parallel configurations to test. Format: "TP DP"
# DSV4-Flash FP8 routed-expert weights ~264 GiB total. Per-die load = 264/TP GiB.
#   TP=2 -> 132 GiB/die > 64 GiB HBM  ❌ OOM expected (kept but will fail)
#   TP=4 ->  66 GiB/die > 64 GiB HBM  ❌ borderline OOM (KV cache leaves no room)
#   TP=8 ->  33 GiB/die < 64 GiB HBM  ✅ fits with room for KV cache
# TP=2/DP=4 and TP=4/DP=2 are likely infeasible for FP8 on 64GB dies; they are
# kept here so the smoke run records the OOM boundary explicitly. Switch to
# INT8 weights (MODEL_PATH=...-INT8, ~132 GiB total) to make TP=4 viable.
if [[ -n "${PARALLEL_CONFIGS_STR:-}" ]]; then
  declare -a PARALLEL_CONFIGS=()
  for pair in $PARALLEL_CONFIGS_STR; do
    PARALLEL_CONFIGS+=("${pair//,/ }")
  done
else
  declare -a PARALLEL_CONFIGS=(
    "2 4"
    "4 2"
    "8 1"
  )
fi

# vLLM-Ascend server settings for DSV4-Flash.
GPU_MEMORY_UTILIZATION="${GPU_MEMORY_UTILIZATION:-0.9}"
KV_CACHE_DTYPE="${KV_CACHE_DTYPE:-fp8}"
BLOCK_SIZE="${BLOCK_SIZE:-128}"
# DSV4-Flash supports up to 1M context, but 64GB HBM/die caps realistic ISL.
# Start at 128K; extend via matrix.json once TP=8 is verified.
MAX_MODEL_LEN="${MAX_MODEL_LEN:-131072}"
MAX_NUM_SEQS="${MAX_NUM_SEQS:-256}"

VLLM_ASCEND_ATTENTION_BACKEND="${VLLM_ASCEND_ATTENTION_BACKEND:-atb}"

DATASET_PATH="${DATASET_PATH:-${ROOT_DIR}/datasets/ShareGPT_V3_unfiltered_cleaned_split.json}"

MATRIX_FILE="${MATRIX_FILE:-${SCRIPT_DIR:-.}/matrix.json}"
MATRIX_MODE="${MATRIX_MODE:-Y}"

export CONCURRENCY_SAMPLES="${CONCURRENCY_SAMPLES:-2}"

SCENARIO_TIMEOUT_S="${SCENARIO_TIMEOUT_S:-1800}"
GPU_MEM_SAMPLE_INTERVAL_S="${GPU_MEM_SAMPLE_INTERVAL_S:-1}"

DRY_RUN="${DRY_RUN:-0}"
GRID_LIMIT="${GRID_LIMIT:-0}"