86 lines
2.2 KiB
YAML
86 lines
2.2 KiB
YAML
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
|
|
apiVersion: nvidia.com/v1alpha1
|
|
kind: DynamoGraphDeployment
|
|
metadata:
|
|
name: fastvideo-agg
|
|
spec:
|
|
pvcs:
|
|
- name: huggingface-cache
|
|
create: false
|
|
services:
|
|
Frontend:
|
|
componentType: frontend
|
|
replicas: 1
|
|
envs:
|
|
- name: DYN_DISCOVERY_BACKEND
|
|
value: kubernetes
|
|
extraPodSpec:
|
|
imagePullSecrets:
|
|
- name: my-image-pull-secret
|
|
tolerations:
|
|
- key: dedicated
|
|
operator: Equal
|
|
value: user-workload
|
|
effect: NoSchedule
|
|
- key: dedicated
|
|
operator: Equal
|
|
value: user-workload
|
|
effect: NoExecute
|
|
mainContainer:
|
|
image: my-registry/fastvideo-runtime:my-tag
|
|
imagePullPolicy: IfNotPresent
|
|
workingDir: /opt/app
|
|
command:
|
|
- python
|
|
- -m
|
|
- dynamo.frontend
|
|
args:
|
|
- --http-port
|
|
- "8000"
|
|
|
|
FastVideoWorker:
|
|
componentType: worker
|
|
replicas: 1
|
|
sharedMemory:
|
|
size: 8Gi
|
|
resources:
|
|
limits:
|
|
gpu: "1"
|
|
requests:
|
|
gpu: "1"
|
|
envs:
|
|
- name: DYN_DISCOVERY_BACKEND
|
|
value: kubernetes
|
|
- name: LD_LIBRARY_PATH
|
|
value: ""
|
|
- name: TORCHINDUCTOR_CACHE_DIR
|
|
value: /cache/torchinductor
|
|
- name: TRITON_CACHE_DIR
|
|
value: /cache/triton
|
|
- name: HF_HOME
|
|
value: /root/.cache/huggingface
|
|
volumeMounts:
|
|
- name: huggingface-cache
|
|
mountPoint: /root/.cache/huggingface
|
|
extraPodSpec:
|
|
imagePullSecrets:
|
|
- name: my-image-pull-secret
|
|
tolerations:
|
|
- key: dedicated
|
|
operator: Equal
|
|
value: user-workload
|
|
effect: NoSchedule
|
|
- key: dedicated
|
|
operator: Equal
|
|
value: user-workload
|
|
effect: NoExecute
|
|
mainContainer:
|
|
image: my-registry/fastvideo-runtime:my-tag
|
|
imagePullPolicy: IfNotPresent
|
|
workingDir: /opt/app
|
|
command:
|
|
- python
|
|
- worker.py
|