227ef603a6
- Restructure repo around experiments/<name>/ and platforms/<chip>.env. - Add shared scripts under scripts/common/ for platform/server/bench-client logic. - Add Kunlun P800 platform config and runtime patches. - Add dsv4_p800_sglang experiment with INT8 smoke-test support. - Update BENCHMARK_WORKFLOW.md and README.md with chip/engine recording rules. - Add scripts/analysis/compare_experiments.py for cross-experiment comparison. - Ignore experiments/*/results/ raw output directories by default.
28 lines
924 B
Bash
28 lines
924 B
Bash
# Platform configuration for Kunlun P800 XPU
|
|
# Source this file via scripts/common/platform.sh
|
|
|
|
CHIP="kunlun_p800"
|
|
ACCELERATOR="Kunlun P800 XPU"
|
|
HARDWARE="8x Kunlun P800 XPU"
|
|
ENGINE="sglang-xpu"
|
|
|
|
# Container runtime
|
|
DOCKER_IMAGE="iregistry.baidu-int.com/xpu/sglang-p800-pd-disagg-0510:20260511_4202"
|
|
CONTAINER_NAME="${CONTAINER_NAME:-sglang-dsv4-flash}"
|
|
|
|
# Device selection
|
|
DEVICE_SELECT_ENV="XPU_VISIBLE_DEVICES=0,1,2,3,4,5,6,7"
|
|
CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
|
CUDA_DEVICE_ORDER="OAM_ID"
|
|
|
|
# Default serving port and model root on the host
|
|
DEFAULT_PORT="30000"
|
|
MODEL_ROOT="/data1/models"
|
|
|
|
# Python interpreter inside the container
|
|
CONTAINER_PYTHON="/root/miniconda/envs/python310_torch25_cuda/bin/python"
|
|
|
|
# Host mount points for patches required by the P800 SGLang image
|
|
# These are baked into the container start command in server_docker.sh.
|
|
PATCH_ROOT="${PATCH_ROOT:-/data1/yy/sskj/platforms/patches/kunlun_p800}"
|