43 lines
1.1 KiB
Bash
Executable File
43 lines
1.1 KiB
Bash
Executable File
#!/bin/bash
|
|
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
# Setup cleanup trap
|
|
cleanup() {
|
|
echo "Cleaning up background processes..."
|
|
kill $DYNAMO_PID $PREFILL_PID 2>/dev/null || true
|
|
wait $DYNAMO_PID $PREFILL_PID 2>/dev/null || true
|
|
echo "Cleanup complete."
|
|
}
|
|
trap cleanup EXIT INT TERM
|
|
|
|
|
|
# run ingress
|
|
python3 -m dynamo.frontend --http-port=8000 &
|
|
DYNAMO_PID=$!
|
|
|
|
# run prefill worker
|
|
python3 -m dynamo.sglang \
|
|
--model-path Qwen/Qwen3-0.6B \
|
|
--served-model-name Qwen/Qwen3-0.6B \
|
|
--page-size 16 \
|
|
--tp 1 \
|
|
--trust-remote-code \
|
|
--disaggregation-mode prefill \
|
|
--disaggregation-bootstrap-port 12345 \
|
|
--host 0.0.0.0 \
|
|
--disaggregation-transfer-backend nixl &
|
|
PREFILL_PID=$!
|
|
|
|
# run decode worker
|
|
CUDA_VISIBLE_DEVICES=1 python3 -m dynamo.sglang \
|
|
--model-path Qwen/Qwen3-0.6B \
|
|
--served-model-name Qwen/Qwen3-0.6B \
|
|
--page-size 16 \
|
|
--tp 1 \
|
|
--trust-remote-code \
|
|
--disaggregation-mode decode \
|
|
--disaggregation-bootstrap-port 12345 \
|
|
--host 0.0.0.0 \
|
|
--disaggregation-transfer-backend nixl
|