- Add dsv4_h20_vllm_tp_dp_matrix experiment (vLLM backend) - Add dsv4_h20_sglang_tp_dp_matrix experiment (SGLang backend) - Add nvidia_h20 platform config with H20-specific paths - Fix platform.sh auto-detection to distinguish H20 from H200 - Fix vLLM Docker startup: remove --entrypoint override for CDI compat - Fix vLLM 0.25.1 CLI args: remove redundant 'serve' from SERVER_ARGS - Download ShareGPT dataset to local datasets dir - Rename DSL to OSL across both experiments
53 lines
1.7 KiB
Bash
Executable File
53 lines
1.7 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 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 -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}"
|