# Long-context matrix for SGLang on DeepSeek-V4-Flash-INT8 (Kunlun P800, TP=8).
# Input lengths: 64k, 128k, 256k
# Output lengths: 256, 1k, 4k
# Concurrency: 25 for 64k; 10, 5, 2 for 128k and 256k

EXPERIMENT="${EXPERIMENT:-dsv4_p800_long_context_matrix}"
MODEL_NAME="${MODEL_NAME:-DeepSeek-V4-Flash-INT8}"
MODEL_PATH="${MODEL_PATH:-/data1/models/DeepSeek-V4-Flash-INT8}"
SERVED_MODEL_NAME="${SERVED_MODEL_NAME:-deepseek-v4-flash-int8}"
PORT="${PORT:-30000}"
BACKEND="${BACKEND:-sglang}"
ENGINE="${ENGINE:-sglang-xpu}"
DATASET="${DATASET:-random}"
DATASET_PATH="${DATASET_PATH:-/workspace/dummy_sharegpt.json}"

# Server launch mode for P800 SGLang.
#   - "w8a8_int8"         : DeepSeek-V4-Flash-INT8 checkpoint with EAGLE speculative decoding
#   - "w8a8_int8_baseline": DeepSeek-V4-Flash-INT8 checkpoint without speculative decoding
SERVER_MODE="${SERVER_MODE:-w8a8_int8_baseline}"

# Per-context server settings. Each group is run with its own server start.
# Format: "input_label context_length max_running"
declare -a CONTEXT_GROUPS=(
  "64k  80000  25"
  "128k 140000 10"
  "256k 270000 10"
)

# Scenarios per group: "concurrency input_len output_len num_prompts"
declare -a SCENARIOS_64K=(
  "25 65536  256  50"
  "25 65536  1024 50"
  "25 65536  4096 50"
)

declare -a SCENARIOS_128K=(
  "10 131072 256  20"
  "5  131072 256  10"
  "2  131072 256  4"
  "10 131072 1024 20"
  "5  131072 1024 10"
  "2  131072 1024 4"
  "10 131072 4096 20"
  "5  131072 4096 10"
  "2  131072 4096 4"
)

declare -a SCENARIOS_256K=(
  "10 262144 256  20"
  "5  262144 256  10"
  "2  262144 256  4"
  "10 262144 1024 20"
  "5  262144 1024 10"
  "2  262144 1024 4"
  "10 262144 4096 20"
  "5  262144 4096 10"
  "2  262144 4096 4"
)

WARMUP="${WARMUP:-0}"