sskj/scripts/common/platform.sh
shishi 46e79d63e7 feat(platform): add Ascend 910C NPU platform support
- platforms/ascend_910c.env: 8-card 910C config (16 dies, 64GB HBM/die),
  Ascend Docker Runtime, ASCEND_VISIBLE_DEVICES device selection
- scripts/common/platform.sh: auto-detect 910C via npu-smi + Huawei PCI IDs
- scripts/common/npu_smi_sampler.py: standalone npu-smi -> nvidia-smi CSV
  sampler so parse_backend.py needs no changes
- experiments/910c/glm52_910c_vllm_tp_dp_matrix/: GLM-5.2 (w4a8c8) experiment,
  model present on host, ready for smoke after image load
- experiments/910c/dsv4_910c_vllm_tp_dp_matrix/: DSV4-Flash experiment
  (placeholder MODEL_PATH, weights not yet downloaded)
- envs/ASCEND_910C_ENV_SETUP.md: full onboarding guide (permissions, image
  load, Ascend Docker Runtime, NPU monitor, known pitfalls)
- Both experiments: TP2/DP4 + TP4/DP2 + TP8/DP1, matrix.json capped at 128K
  context per 64GB HBM/die
2026-07-27 22:00:05 +08:00

68 lines
2.4 KiB
Bash
Executable File

#!/usr/bin/env bash
# Platform loader.
# Usage: source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/../scripts/common/platform.sh"
set -Eeuo pipefail
_PLATFORM_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ROOT_DIR="$(cd "${_PLATFORM_DIR}/../.." && pwd)"
# Auto-detect platform if not set.
if [[ -z "${PLATFORM:-}" ]]; then
# Capture xpu-smi output first; piping it directly can trigger SIGPIPE under
# pipefail when grep -q exits early.
_XPU_SMI_OUT=""
if command -v xpu-smi >/dev/null 2>&1; then
_XPU_SMI_OUT=$(xpu-smi 2>/dev/null || true)
fi
if [[ -n "$_XPU_SMI_OUT" ]] && grep -qiE "P800|Kunlun" <<< "$_XPU_SMI_OUT"; then
PLATFORM="kunlun_p800"
elif lspci 2>/dev/null | grep -qiE "XPU|Kunlun"; then
PLATFORM="kunlun_p800"
elif command -v npu-smi >/dev/null 2>&1; then
# Huawei Ascend NPU. npu-smi info lists cards like "Ascend910" / "910C".
_NPU_SMI_OUT=$(npu-smi info 2>/dev/null || true)
if [[ -n "$_NPU_SMI_OUT" ]] && grep -qiE "Ascend910|Ascend 910|910C|910c" <<< "$_NPU_SMI_OUT"; then
PLATFORM="ascend_910c"
else
PLATFORM="ascend_910c"
fi
unset _NPU_SMI_OUT
elif lspci 2>/dev/null | grep -qiE "Huawei.*a12d|Huawei.*a12e|d100|d80"; then
# Ascend 910 series exposes Huawei System-peripheral PCI IDs (a12d/a12e).
PLATFORM="ascend_910c"
elif command -v nvidia-smi >/dev/null 2>&1; then
_GPU_NAME=$(nvidia-smi --query-gpu=name --format=csv,noheader 2>/dev/null | head -n 1 || true)
if [[ -n "$_GPU_NAME" ]] && grep -qiE "RTX 6000D|PRO 6000D" <<< "$_GPU_NAME"; then
PLATFORM="nvidia_rtx6000d"
elif [[ -n "$_GPU_NAME" ]] && grep -qi "H20" <<< "$_GPU_NAME"; then
PLATFORM="nvidia_h20"
else
PLATFORM="nvidia_h200"
fi
unset _GPU_NAME
else
echo "ERROR: Could not auto-detect PLATFORM. Set PLATFORM env var explicitly." >&2
exit 1
fi
unset _XPU_SMI_OUT
echo "Auto-detected platform: ${PLATFORM}"
fi
PLATFORM_FILE="${ROOT_DIR}/platforms/${PLATFORM}.env"
if [[ ! -f "$PLATFORM_FILE" ]]; then
echo "ERROR: Platform config not found: ${PLATFORM_FILE}" >&2
exit 1
fi
# shellcheck source=/dev/null
source "$PLATFORM_FILE"
# Export key variables if not already set.
export CHIP="${CHIP:-$PLATFORM}"
export ACCELERATOR="${ACCELERATOR:-$PLATFORM}"
export HARDWARE="${HARDWARE:-$PLATFORM}"
export DEFAULT_PORT="${DEFAULT_PORT:-30000}"
export MODEL_ROOT="${MODEL_ROOT:-/data1/models}"