Add ability to scale on tgi custom metrics #263
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
See changes for details. Some extra reasoning behind the changes: * Prefix all GCS buckets with project_id since GCS buckets are globally namespaced. * gcloud storage buckets add-iam-policy-binding" only accepts bucket URLs
This allows the tgi workload to scale up based on CPU demand (and eventually other metrics). NB: CPU is a poor choice for this workload, but acts as a baseline that we can use to evaluate other metrics.
...hmarks/inference-server/text-generation-inference/hpa-templates/tgi-podmonitoring.yaml.tftpl
Outdated
Show resolved
Hide resolved
...ks/inference-server/text-generation-inference/hpa-templates/hpa.tgi.custom_metric.yaml.tftpl
Outdated
Show resolved
Hide resolved
...hmarks/inference-server/text-generation-inference/custom-metrics-stackdriver-adapter/main.tf
Outdated
Show resolved
Hide resolved
benchmarks/inference-server/text-generation-inference/sample-terraform.tfvars
Outdated
Show resolved
Hide resolved
...hmarks/inference-server/text-generation-inference/custom-metrics-stackdriver-adapter/main.tf
Outdated
Show resolved
Hide resolved
...arks/inference-server/text-generation-inference/custom-metrics-stackdriver-adapter/README.md
Show resolved
Hide resolved
benchmarks/inference-server/text-generation-inference/sample-terraform.tfvars
Show resolved
Hide resolved
laoj2
reviewed
Mar 5, 2024
annapendleton
approved these changes
Mar 5, 2024
|
/gcbrun |
|
/gcbrun |
|
/gcbrun |
|
/gcbrun |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.