1482601ae5
- Document the rule in docs/EXPERIMENT_GUIDE.md section 7 - Update all config.env SCENARIOS to follow the 5x rule - Migrate dsv4_h200_sglang, dsv4_h200_vllm, dsv4_p800_sglang from global NUM_PROMPTS to per-scenario num_prompts - Keep long-context phase2 as exception (low counts documented) - Add legacy 3-field fallback in run_bench.sh loops
35 lines
1.1 KiB
Bash
35 lines
1.1 KiB
Bash
# Template configuration for a SGLang vs vLLM benchmark experiment.
|
|
# Copy this directory to experiments/<your_experiment_name>/ and adjust the values.
|
|
|
|
EXPERIMENT="TEMPLATE"
|
|
MODEL_NAME="DeepSeek-V4-Flash"
|
|
MODEL_PATH="/data/models/DeepSeek-V4-Flash"
|
|
SERVED_MODEL_NAME="deepseek-v4-flash"
|
|
|
|
SGLANG_PORT="${SGLANG_PORT:-30006}"
|
|
VLLM_PORT="${VLLM_PORT:-30005}"
|
|
|
|
VENV_SGLANG="${VENV_SGLANG:-/data/user1/yy/envs/sglang}"
|
|
VENV_VLLM="${VENV_VLLM:-/data/user1/yy/envs/vllm}"
|
|
|
|
# Hardware: override in platforms/<chip>.env or set explicitly.
|
|
export CUDA_VISIBLE_DEVICES="${CUDA_VISIBLE_DEVICES:-0,1,2,3,4,5,6,7}"
|
|
TP="${TP:-8}"
|
|
|
|
# Server limits.
|
|
MAX_MODEL_LEN="${MAX_MODEL_LEN:-32768}"
|
|
MAX_NUM_SEQS="${MAX_NUM_SEQS:-256}"
|
|
MAX_RUNNING="${MAX_RUNNING:-256}"
|
|
|
|
# Scenarios: "concurrency input_len output_len num_prompts".
|
|
# Following docs/EXPERIMENT_GUIDE.md: num_prompts = concurrency * 5.
|
|
declare -a SCENARIOS=(
|
|
"1 512 256 5"
|
|
"32 512 256 160"
|
|
)
|
|
|
|
VENV_CLIENT="${VENV_CLIENT:-$VENV_SGLANG}"
|
|
|
|
SGLANG_START_SCRIPT="${SCRIPT_DIR:-.}/start_sglang.sh"
|
|
VLLM_START_SCRIPT="${SCRIPT_DIR:-.}/start_vllm.sh"
|