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
36 lines
1.2 KiB
Bash
36 lines
1.2 KiB
Bash
# Configuration for vLLM MTP speculative decoding vs vLLM default comparison on H200.
|
|
# The default-side results are reused from dsv4_h200_vllm_dspark_vs_default/results/20260708-142121/default.
|
|
|
|
EXPERIMENT="dsv4_h200_vllm_mtp_vs_default"
|
|
MODEL_NAME="DeepSeek-V4-Flash"
|
|
MODEL_PATH="/data/models/DeepSeek-V4-Flash"
|
|
SERVED_MODEL_NAME="deepseek-v4-flash"
|
|
|
|
MTP_PORT="${MTP_PORT:-30009}"
|
|
DEFAULT_RESULT_ROOT="${DEFAULT_RESULT_ROOT:-/data/user1/yy/experiments/dsv4_h200_vllm_dspark_vs_default/results/20260708-142121/default}"
|
|
|
|
VENV_VLLM="${VENV_VLLM:-/data/user1/yy/envs/vllm}"
|
|
VENV_CLIENT="${VENV_CLIENT:-/data/user1/yy/envs/sglang}"
|
|
|
|
export CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
|
|
TP=8
|
|
|
|
MAX_MODEL_LEN=32768
|
|
MAX_NUM_SEQS=256
|
|
SPEC_METHOD="${SPEC_METHOD:-mtp}"
|
|
SPEC_TOKENS="${SPEC_TOKENS:-1}"
|
|
|
|
# Scenarios must match the ones in the reused default result set.
|
|
# Following docs/EXPERIMENT_GUIDE.md: num_prompts = concurrency * 5.
|
|
# NOTE: if these scenarios are changed, the default-side results must be re-run
|
|
# with the same scenarios (update DEFAULT_RESULT_ROOT accordingly).
|
|
declare -a SCENARIOS=(
|
|
"1 512 256 5"
|
|
"32 512 256 160"
|
|
"128 512 256 640"
|
|
"1 4000 512 5"
|
|
"32 4000 512 160"
|
|
)
|
|
|
|
MTP_START_SCRIPT="${SCRIPT_DIR:-.}/start_mtp.sh"
|