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
68 lines
2.1 KiB
Bash
68 lines
2.1 KiB
Bash
# Common configuration for the SGLang vs vLLM comparison on H200.
|
|
# All values can be overridden via environment variables.
|
|
|
|
EXPERIMENT="dsv4_h200_sglang_vs_vllm"
|
|
MODEL_NAME="DeepSeek-V4-Flash"
|
|
MODEL_PATH="/data/models/DeepSeek-V4-Flash"
|
|
SERVED_MODEL_NAME="deepseek-v4-flash"
|
|
|
|
# Ports must differ so both backends can be tested independently.
|
|
SGLANG_PORT="${SGLANG_PORT:-30006}"
|
|
VLLM_PORT="${VLLM_PORT:-30005}"
|
|
|
|
# Virtual environments.
|
|
VENV_SGLANG="${VENV_SGLANG:-/data/user1/yy/envs/sglang}"
|
|
VENV_VLLM="${VENV_VLLM:-/data/user1/yy/envs/vllm}"
|
|
|
|
# Hardware: use all 8 H200 cards for both backends.
|
|
export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
|
TP=8
|
|
|
|
# Phase 1: short-context throughput (max_model_len 32k).
|
|
# Each element: "concurrency input_len output_len num_prompts"
|
|
# Following docs/EXPERIMENT_GUIDE.md: num_prompts = concurrency * 5.
|
|
if [[ -z "${PHASE1_SCENARIOS:-}" ]]; then
|
|
declare -a PHASE1_SCENARIOS=(
|
|
"1 512 256 5"
|
|
"32 512 256 160"
|
|
"128 512 256 640"
|
|
"1 4000 512 5"
|
|
"32 4000 512 160"
|
|
)
|
|
fi
|
|
PHASE1_MAX_MODEL_LEN=32768
|
|
PHASE1_MAX_NUM_SEQS=256
|
|
PHASE1_MAX_RUNNING=256
|
|
|
|
# Phase 2: long context (max_model_len 210k to leave room for output + padding).
|
|
# Exception to the 5x rule due to very long input lengths; kept at low counts.
|
|
if [[ -z "${PHASE2_SCENARIOS:-}" ]]; then
|
|
declare -a PHASE2_SCENARIOS=(
|
|
"1 32768 1024 8"
|
|
"1 65536 1024 4"
|
|
"1 131072 1024 2"
|
|
"1 200000 1024 1"
|
|
)
|
|
fi
|
|
PHASE2_MAX_MODEL_LEN=210000
|
|
PHASE2_MAX_NUM_SEQS=2
|
|
PHASE2_MAX_RUNNING=2
|
|
|
|
# ShareGPT dataset test (uses the same max_model_len as Phase 1).
|
|
SHAREGPT_DATASET="${SHAREGPT_DATASET:-/data/user1/yy/datasets/ShareGPT_filtered_chat.json}"
|
|
SHAREGPT_CONTEXT_LEN=32768
|
|
if [[ -z "${SHAREGPT_SCENARIOS:-}" ]]; then
|
|
declare -a SHAREGPT_SCENARIOS=(
|
|
"1 32768 256 5"
|
|
"32 32768 256 160"
|
|
)
|
|
fi
|
|
|
|
# Benchmark client always runs from the sglang env so that the same
|
|
# sglang.bench_serving version is used for both backends.
|
|
VENV_CLIENT="${VENV_CLIENT:-$VENV_SGLANG}"
|
|
|
|
# Server start scripts bundled with this experiment.
|
|
SGLANG_START_SCRIPT="${SCRIPT_DIR:-.}/start_sglang.sh"
|
|
VLLM_START_SCRIPT="${SCRIPT_DIR:-.}/start_vllm.sh"
|