llama.yaml

# 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: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
  kv-transfer-config: '{"kv_connector":"NixlConnector","kv_role":"kv_both"}'
  max-model-len: 208960

Frontend:
  common-configs: [model]

Processor:
  router: round-robin
  prompt-template: "<|image|>\n<prompt>"
  common-configs: [model, block-size, max-model-len]

VllmDecodeWorker:
  router: random
  tensor_parallel_size: 8
  ServiceArgs:
    workers: 1
    resources:
      gpu: '8'
  common-configs: [model, kv-transfer-config, block-size, max-model-len]

VllmPDWorker:
  enable_disagg: false
  router: random
  tensor_parallel_size: 8
  ServiceArgs:
    workers: 1
    resources:
      gpu: '8'
  common-configs: [model, kv-transfer-config, block-size, max-model-len]