# Qwen3-235B-A22B SGLang TP=8 profile on a single RTX 6000D node (8 GPUs).
# NVIDIA counterpart of p800/qwen3_235b_p800_sglang_tp8 (same workload for
# comparability: isl=2048 osl=2048 c=16).

PLATFORM=pro6000
EXPERIMENT=qwen3_235b_pro6000_sglang_tp8
MODEL_NAME=Qwen3-235B-A22B
ENGINE=sglang
RUNTIME=docker
DOCKER_IMAGE=sglang-sm120-dsv4:0.5.15.post1-fi0.6.14-sm120fix1
CONTAINER_NAME=qwen3_235b_pro6000_sglang_tp8
MODEL_PATH=/data/6000D/Qwen3-235B-A22B
SERVED_MODEL_NAME=/data/6000D/Qwen3-235B-A22B
PORT=30010
HEALTH_PATH=/health
HEALTH_WAIT_S=1800
CONTAINER_PYTHON=python3
TP=8

DEVICE_VARS="CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7"
ENGINE_ENV="PYTHONUNBUFFERED=1 HF_HUB_OFFLINE=1 TRANSFORMERS_OFFLINE=1 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True"

DOCKER_FLAGS="--gpus all --privileged --ipc=host --network host --ulimit memlock=-1 --ulimit stack=67108864"
VOLUMES="/data:/data"

LAUNCH_ARGS="--model-path ${MODEL_PATH} --trust-remote-code --tp-size ${TP} --mem-fraction-static 0.9 --context-length 8192 --max-running-requests 16 --host 0.0.0.0 --port ${PORT}"