agg.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.
tensor_parallel_size: 1
moe_expert_parallel_size: 1
enable_attention_dp: false
max_num_tokens: 8192
max_batch_size: 16
trust_remote_code: true
backend: pytorch
enable_chunked_prefill: true

kv_cache_config:
  free_gpu_memory_fraction: 0.85

# NOTE: pytorch_backend_config section flattened since: https://github.com/NVIDIA/TensorRT-LLM/pull/4603
# NOTE: overlap_scheduler enabled by default since this commit and changed
# config field from 'enable_overlap_scheduler' to 'disable_overlap_scheduler':
# https://github.com/NVIDIA/TensorRT-LLM/commit/b4e5df0ee0024eda3eeb83a6ba822245a30ab428


cuda_graph_config:
  max_batch_size: 16