90fc378d2b
- 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
25 lines
841 B
Bash
25 lines
841 B
Bash
# Platform configuration for NVIDIA H20
|
|
# Source this file via scripts/common/platform.sh
|
|
|
|
CHIP="nvidia_h20"
|
|
ACCELERATOR="NVIDIA H20"
|
|
HARDWARE="8x NVIDIA H20 96GB"
|
|
ENGINE="vllm"
|
|
|
|
# Device selection
|
|
DEVICE_SELECT_ENV="CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7"
|
|
CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
|
|
|
# Default serving port and model root on the host
|
|
DEFAULT_PORT="30004"
|
|
MODEL_ROOT="/data1/hf_models"
|
|
|
|
# Virtual environments on the host (used by native H20 scripts).
|
|
# Override these if your H20 machine uses different paths.
|
|
VENV_VLLM="${VENV_VLLM:-/data1/yy/sskj/envs/vllm}"
|
|
VENV_SGLANG="${VENV_SGLANG:-/data1/yy/sskj/envs/sglang}"
|
|
VENV_CLIENT="${VENV_CLIENT:-/data1/yy/sskj/envs/sglang}"
|
|
|
|
# Default server start script for the legacy benchmark grid.
|
|
SERVER_START_SCRIPT="${SERVER_START_SCRIPT:-${ROOT_DIR}/scripts/start_dsv4_dspark_8card.sh}"
|