Skip to content

Upgrade deepgram images to release 250610 #2546

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
beastoin merged 3 commits into from
Jun 14, 2025
Merged

Upgrade deepgram images to release 250610 #2546

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a644ff9
Upgrade Deepgram images to release-250505
thainguyensunya Jun 2, 2025
2e13fa0
Merge branch 'main' of github.com:BasedHardware/omi into task/upgrade…
thainguyensunya Jun 14, 2025
65e4d35
Update Deepgram images to release-250610
thainguyensunya Jun 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions backend/charts/deepgram-self-hosted/nova-3/dev_omi_values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,29 +53,29 @@ scaling:
batch:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
streaming:
requestsPerPod:
requestsPerPod: 30
textToSpeech:
batch:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
# Discuss a reasoanble value with your Deepgram Account Representative
# Must also set engine.concurrencyLimit.activeRequests if using request ratio for autoscaling
requestCapacityRatio:
custom:
- type: External
external:
metric:
name: engine_avg_gpu_utilization
target:
type: Value
value: 70
# custom:
# - type: External
# external:
# metric:
# name: engine_avg_gpu_utilization
# target:
# type: Value
# value: 70
behavior:
scaleUp:
stabilizationWindowSeconds: 120 # Wait 2 minutes before scaling up

api:
image:
path: us-central1-docker.pkg.dev/based-hardware-dev/deepgram/self-hosted-api
tag: release-250505
tag: release-250610
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
Expand Down Expand Up @@ -108,7 +108,7 @@ api:
engine:
image:
path: us-central1-docker.pkg.dev/based-hardware-dev/deepgram/self-hosted-engine
tag: release-250505
tag: release-250610
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
Expand Down Expand Up @@ -144,7 +144,7 @@ licenseProxy:
enabled: true
image:
path: us-central1-docker.pkg.dev/based-hardware-dev/deepgram/self-hosted-license-proxy
tag: release-250505
tag: release-250610
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
Expand Down
26 changes: 13 additions & 13 deletions backend/charts/deepgram-self-hosted/nova-3/prod_omi_values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,37 +45,37 @@ scaling:

engine:
# -- Minimum number of Engine replicas.
minReplicas: 5
minReplicas: 10
# -- Maximum number of Engine replicas.
maxReplicas: 20
metrics:
speechToText:
batch:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
streaming:
requestsPerPod:
requestsPerPod: 30
textToSpeech:
batch:
requestsPerPod: # Discuss a reasonable value with your Deepgram Account Representative
# Discuss a reasoanble value with your Deepgram Account Representative
# Must also set engine.concurrencyLimit.activeRequests if using request ratio for autoscaling
requestCapacityRatio:
custom:
- type: External
external:
metric:
name: engine_avg_gpu_utilization
target:
type: Value
value: 60
# custom:
# - type: External
# external:
# metric:
# name: engine_avg_gpu_utilization
# target:
# type: Value
# value: 60
behavior:
scaleUp:
stabilizationWindowSeconds: 60 # Wait 1 minute before scaling up

api:
image:
path: us-central1-docker.pkg.dev/based-hardware/deepgram/self-hosted-api
tag: release-250505
tag: release-250610
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
Expand Down Expand Up @@ -108,7 +108,7 @@ api:
engine:
image:
path: us-central1-docker.pkg.dev/based-hardware/deepgram/self-hosted-engine
tag: release-250505
tag: release-250610
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
Expand Down Expand Up @@ -144,7 +144,7 @@ licenseProxy:
enabled: true
image:
path: us-central1-docker.pkg.dev/based-hardware/deepgram/self-hosted-license-proxy
tag: release-250505
tag: release-250610
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
Expand Down