dgx-spark-playbooks/nvidia/sglang/assets/offline-inference.py
2025-11-25 20:28:09 +00:00

30 lines
1.0 KiB
Python

#
# SPDX-FileCopyrightText: Copyright (c) 1993-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import sglang as sgl
def main():
llm = sgl.Engine(model_path="deepseek-ai/DeepSeek-V2-Lite", trust_remote_code=True)
prompt = "What does NVIDIA love?"
sampling_params = {"temperature": 0.7, "max_new_tokens": 100}
output = llm.generate(prompt, sampling_params)
print(f"Output: {output}")
if __name__ == '__main__':
main()