8e15ffe1c7
- Move dspark_deepseekv4_fix_pr_prep.md into experiments/dsv4_h200_dspark/ - Move dsv4_inference_comparison_report.md into docs/ - Delete obsolete cleanup_summary.md - Add experiments/dsv4_h200_vllm/ baseline experiment (envs/vllm + envs/sglang)
25 lines
957 B
Bash
25 lines
957 B
Bash
# Experiment-level configuration for dsv4_h200_vllm
|
|
# All values can be overridden via environment variables.
|
|
|
|
EXPERIMENT="${EXPERIMENT:-dsv4_h200_vllm}"
|
|
MODEL_NAME="${MODEL_NAME:-DeepSeek-V4-Flash}"
|
|
MODEL_PATH="${MODEL_PATH:-/data/models/DeepSeek-V4-Flash}"
|
|
SERVED_MODEL_NAME="${SERVED_MODEL_NAME:-deepseek-v4-flash}"
|
|
PORT="${PORT:-30005}"
|
|
# This experiment is a plain vLLM baseline. These values override the
|
|
# vllm-dspark defaults coming from platforms/nvidia_h200.env.
|
|
BACKEND="vllm"
|
|
ENGINE="vllm"
|
|
|
|
# Native virtual environments on the host.
|
|
VENV_SERVER="${VENV_SERVER:-/data/user1/yy/envs/vllm}"
|
|
VENV_CLIENT="${VENV_CLIENT:-/data/user1/yy/envs/sglang}"
|
|
|
|
# Benchmark scenarios: "concurrency input_len output_len".
|
|
# Override via SCENARIOS env var.
|
|
SCENARIOS="${SCENARIOS:-32 512 256 128 512 256 32 4000 512}"
|
|
NUM_PROMPTS="${NUM_PROMPTS:-128}"
|
|
|
|
# Server start script bundled with this experiment.
|
|
SERVER_START_SCRIPT="${SCRIPT_DIR}/start_server.sh"
|