llm_api_config.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.


# In the case of disaggregated deployment, this config will apply to each server
# and will be overwritten by the disaggregated config file

model_name: "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
model_path: null
tensor_parallel_size: 1
moe_expert_parallel_size: 1
enable_attention_dp: false
max_num_tokens: 10240
max_batch_size: 16
trust_remote_code: true
backend: pytorch

kv_cache_config:
  free_gpu_memory_fraction: 0.95
  # Uncomment to enable kv cache event collection
  #event_buffer_max_size: 1024
  #enable_block_reuse: true

pytorch_backend_config:
  enable_overlap_scheduler: false
  use_cuda_graph: false
  # Uncomment to enable iter perf stats
  #enable_iter_perf_stats: true