# Platform configuration for Huawei Ascend 910C NPU # Source this file via scripts/common/platform.sh # # Host reference (910c.1 / NPU-NODE61): # - openEuler 22.03 SP4, aarch64, 8x Ascend910 (16 dies, 64GB HBM/die) # - CANN 9.0.0 + ascend-toolkit, driver 25.5.2 # - Ascend Docker Runtime is the default docker runtime (see /etc/docker/daemon.json) # - User must be in HwHiAiUser + docker groups to access NPU devices and docker. CHIP="ascend_910c" ACCELERATOR="Huawei Ascend 910C" HARDWARE="8x Ascend910 (16 dies, 64GB HBM/die)" ENGINE="vllm-ascend" # Container runtime. vllm-ascend images ship as tarballs on this host and must # be `docker load`-ed first (see envs/ASCEND_910C_ENV_SETUP.md). The exact tag # is overridden per-experiment in config.env; this is the default for new ones. # Known-good tarballs on /mnt/models: # vllm-ascend-v0.23.0rc1-a3-openeuler.tar -> general vllm-ascend # vllm-ascend-glm5.2-a3-openeuler.tar -> GLM5.2-tuned variant DOCKER_IMAGE="${DOCKER_IMAGE:-quay.io/ascend/vllm-ascend:latest}" CONTAINER_NAME="${CONTAINER_NAME:-vllm-ascend-910c}" # Device selection. Ascend Docker Runtime maps NPU dies via ASCEND_VISIBLE_DEVICES # (0-based NPU card id). 8 cards => 0..7. Each card exposes 2 dies; vllm-ascend # addresses dies individually so TP can go up to 16. DEVICE_SELECT_ENV="ASCEND_VISIBLE_DEVICES=0,1,2,3,4,5,6,7" ASCEND_VISIBLE_DEVICES="${ASCEND_VISIBLE_DEVICES:-0,1,2,3,4,5,6,7}" # Default serving port and model root on the host. # /mnt/models holds GLM-5.2-{w4a8c8,w8a8} and vllm-ascend image tarballs. DEFAULT_PORT="30050" MODEL_ROOT="/mnt/models" # Python interpreter inside the vllm-ascend container (used to run the # benchmark client via `docker exec`). Standard path in the official image. CONTAINER_PYTHON="${CONTAINER_PYTHON:-/usr/local/bin/python}" # CANN / toolkit paths on the host (informational; the container bundles its # own CANN). Referenced by env setup docs, not by run scripts directly. HOST_CANN_ROOT="/usr/local/Ascend/ascend-toolkit/latest" HOST_DRIVER_VERSION="25.5.2"