agg.yaml 1.17 KB
Newer Older
1
# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
2
3
4
5
6
7
8
9
10
# SPDX-License-Identifier: Apache-2.0

apiVersion: nvidia.com/v1alpha1
kind: DynamoGraphDeployment
metadata:
  name: sglang-agg
spec:
  services:
    Frontend:
11
      componentType: frontend
12
13
14
15
      replicas: 1
      extraPodSpec:
        mainContainer:
          image: my-registry/sglang-runtime:my-tag
16
    decode:
17
18
19
20
21
22
      envFromSecret: hf-token-secret
      componentType: worker
      replicas: 1
      resources:
        limits:
          gpu: "1"
23
24
25
26
        requests:
          custom:
            # Increase this value for larger models
            ephemeral-storage: "2Gi"
27
28
29
      extraPodSpec:
        mainContainer:
          image: my-registry/sglang-runtime:my-tag
30
          workingDir: /workspace/examples/backends/sglang
31
          command:
32
33
34
          - python3
          - -m
          - dynamo.sglang
35
          args:
36
37
38
39
40
41
42
43
44
45
            - --model-path
            - Qwen/Qwen3-0.6B
            - --served-model-name
            - Qwen/Qwen3-0.6B
            - --page-size
            - "16"
            - --tp
            - "1"
            - --trust-remote-code
            - --skip-tokenizer-init
julienmancuso's avatar
julienmancuso committed
46