# 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.

# This is a sample config for TensorRT-LLM engine.
# The config provides smaller free_gpu_memory_fraction to ensure that the engine
# does not use all the GPU memory and both prefill and decode workers can fit in
# the GPU memory when running in disaggregated mode.
# You might have to tweak this config based on your model size and GPU memory.

backend: pytorch
disable_overlap_scheduler: true
kv_cache_config:
  free_gpu_memory_fraction: 0.40