8b82f700e4
- Add experiments/dsv4_h200_sglang (config, server start, orchestrator, parser, README) - Fix start_server.sh to wait for HTTP 200 via curl --fail instead of treating 503 as ready - Add H200 SGLang baseline to root README and update .gitignore for per-run raw_outputs/logs - Remove stale experiments/dsv4_h200_dspark/DSPARK_FIX_PR_PREP.md
29 lines
977 B
Bash
29 lines
977 B
Bash
# Experiment-level configuration for dsv4_h200_sglang
|
|
# All values can be overridden via environment variables.
|
|
|
|
EXPERIMENT="${EXPERIMENT:-dsv4_h200_sglang}"
|
|
MODEL_NAME="${MODEL_NAME:-DeepSeek-V4-Flash}"
|
|
MODEL_PATH="${MODEL_PATH:-/data/models/DeepSeek-V4-Flash}"
|
|
SERVED_MODEL_NAME="${SERVED_MODEL_NAME:-deepseek-v4-flash}"
|
|
PORT="${PORT:-30006}"
|
|
# This experiment is a plain SGLang baseline. These values override the
|
|
# vllm-dspark defaults coming from platforms/nvidia_h200.env.
|
|
BACKEND="sglang"
|
|
ENGINE="sglang"
|
|
|
|
# Native virtual environments on the host.
|
|
VENV_SERVER="${VENV_SERVER:-/data/user1/yy/envs/sglang}"
|
|
VENV_CLIENT="${VENV_CLIENT:-/data/user1/yy/envs/sglang}"
|
|
|
|
# Benchmark scenarios: each element is "concurrency input_len output_len".
|
|
if [[ -z "${SCENARIOS:-}" ]]; then
|
|
SCENARIOS=(
|
|
"32 512 256"
|
|
"128 512 256"
|
|
)
|
|
fi
|
|
NUM_PROMPTS="${NUM_PROMPTS:-128}"
|
|
|
|
# Server start script bundled with this experiment.
|
|
SERVER_START_SCRIPT="${SCRIPT_DIR}/start_server.sh"
|