# 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: llava-hf/LLaVA-NeXT-Video-7B-hf
  block-size: 64
  max-model-len: 4096
  num-sampled-frames: 8
  frame-height: 336
  frame-width: 336
  frame-channels: 3
  dummy-token-id: 0
  video-token-id: 32000
  dummy-tokens-per-frame: 144

Frontend:
  common-configs: [model]

Processor:
  router: round-robin
  common-configs: [model, block-size, max-model-len]

VllmDecodeWorker:
  enforce-eager: true
  max-num-batched-tokens: 16384
  enable-prefix-caching: true
  router: random
  tensor-parallel-size: 1
  ServiceArgs:
    workers: 1
    resources:
      gpu: 1
  common-configs: [model, block-size, max-model-len, num-sampled-frames, frame-height, frame-width, frame-channels, dummy-token-id, video-token-id, dummy-tokens-per-frame]

VllmEncodeWorker:
  tensor-parallel-size: 1
  router: random
  ServiceArgs:
    workers: 1
    resources:
      gpu: 1
  common-configs: [model, num-sampled-frames, frame-height, frame-width, frame-channels, dummy-token-id, video-token-id, dummy-tokens-per-frame]