# SPDX-FileCopyrightText: Copyright (c) 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.
Common:
  model: Qwen/Qwen2.5-VL-7B-Instruct
  block-size: 64
  max-model-len: 4096

Frontend:
  common-configs: [model]

Processor:
  router: round-robin
  prompt-template: "<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|><prompt><|im_end|>\n<|im_start|>assistant\n"
  common-configs: [model, block-size, max-model-len]

VllmDecodeWorker:
  enforce-eager: true
  max-num-batched-tokens: 16384
  max-num-seqs: 5
  mm-processor-kwargs:
    min_pixels: 784
    max_pixels: 1003520
    fps: 1
  enable-prefix-caching: true
  image-token-id: 151655
  num-patches: 345
  router: random
  tensor-parallel-size: 1
  ServiceArgs:
    workers: 1
    resources:
      gpu: '1'
  common-configs: [model, block-size, max-model-len]

VllmEncodeWorker:
  tensor-parallel-size: 1
  router: random
  ServiceArgs:
    workers: 1
    resources:
      gpu: '1'
  common-configs: [model]