".dockerignore" did not exist on "f86fc334b06ade6fcf04023b1880ef4650480248"
disagg.yaml 1.36 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
# 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.

16

17
18
Frontend:
  model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
19
  endpoint: dynamo.Processor.chat/completions
20
21
22
23
  port: 8000

Processor:
  model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
24
  router: round-robin
25
26

VllmWorker:
27
  # vllm enging args
28
29
30
  model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
  kv-transfer-config: '{"kv_connector":"DynamoNixlConnector"}'
  max-model-len: 16384
31
32
33

  # dynamo args
  remote-prefill: true
34
  conditional-disagg: true
35
  max-local-prefill-length: 10
36
37

PrefillWorker:
38
  # vllm enging args
39
40
41
  model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
  kv-transfer-config: '{"kv_connector":"DynamoNixlConnector"}'
  max-model-len: 16384
42
43

  # dynamo arg for local deployment
44
  cuda-visible-device-offset: 1