EXPERIMENT_BASE=kimi3_pro6000_dp2_nospec_ab
IMAGE=local/sglang:kimi-k3-pp-dflash-33863-fi0618-situ4460-kvbounds1
MODEL_PATH=/data/hf_models/Kimi-K3
DRAFT_MODEL_PATH=/data/hf_models/Kimi-K3-DFlash
DFLASH_FIX_SOURCE=/data/hzy/sskj/experiments/pro6000/cdflash_fix
DFLASH_FIX_DIR=/data/hzy/kimi3_dp2_dflash_fix
DFLASH_FIX_MAP=(
  arg_groups/speculative_hook.py
  arg_groups/validation_hook.py
  speculative/dflash_worker_v2.py
)

REPLICA_A_NODES=(174.1.60.1 174.1.60.2 174.1.60.3 174.1.60.4)
REPLICA_B_NODES=(174.1.60.5 174.1.60.6 174.1.60.7 174.1.60.8)
SSH_USER=user
SSH_OPTIONS=(-o BatchMode=yes -o ConnectTimeout=10)

SERVER_PORT=30000
DIST_PORT=20000
ROUTER_PORT=32000
EP_SIZE=4
CHUNK_SIZE=8192
PAGE_SIZE=64
KV_DTYPE=bfloat16
MAX_RUNNING_REQUESTS=8
CUDA_GRAPH_MAX_BS=8
DRAFT_TOKENS=16
IB_DEVICES=mlx5_0,mlx5_1,mlx5_2,mlx5_3
NCCL_DEBUG_LEVEL=${NCCL_DEBUG_LEVEL:-WARN}
JIT_CACHE=/data/hzy/cache/kimi-dflash-fi0618-situ4460
HEALTH_WAIT_S=2400

SPEED_BENCH_DATASET=/data/speedbench16k_complete.jsonl
NUM_PROMPTS=40
OUTPUT_LEN=512
CONCURRENCY=8