generated from kubernetes/kubernetes-template-project
-
Notifications
You must be signed in to change notification settings - Fork 90
add regression testing docs #755
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.
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
+918
−19
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
237 changes: 237 additions & 0 deletions
237
config/manifests/regression-testing/inferencemodel.yaml
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,237 @@ | ||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-0 | ||
| spec: | ||
| modelName: adapter-0 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-0 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-1 | ||
| spec: | ||
| modelName: adapter-1 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-1 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-2 | ||
| spec: | ||
| modelName: adapter-2 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-2 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-3 | ||
| spec: | ||
| modelName: adapter-3 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-3 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-4 | ||
| spec: | ||
| modelName: adapter-4 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-4 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-5 | ||
| spec: | ||
| modelName: adapter-5 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-5 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-6 | ||
| spec: | ||
| modelName: adapter-6 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-6 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-7 | ||
| spec: | ||
| modelName: adapter-7 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-7 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-8 | ||
| spec: | ||
| modelName: adapter-8 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-8 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-9 | ||
| spec: | ||
| modelName: adapter-9 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-9 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-10 | ||
| spec: | ||
| modelName: adapter-10 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-10 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-11 | ||
| spec: | ||
| modelName: adapter-11 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-11 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-12 | ||
| spec: | ||
| modelName: adapter-12 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-12 | ||
| weight: 100 | ||
|
|
||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-13 | ||
| spec: | ||
| modelName: adapter-13 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-13 | ||
| weight: 100 | ||
|
|
||
|
|
||
| --- | ||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: adapter-14 | ||
| spec: | ||
| modelName: adapter-14 | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct | ||
| targetModels: | ||
| - name: adapter-14 | ||
| weight: 100 | ||
|
|
||
| --- | ||
|
|
||
|
|
||
| apiVersion: inference.networking.x-k8s.io/v1alpha2 | ||
| kind: InferenceModel | ||
| metadata: | ||
| name: base-model | ||
| spec: | ||
| modelName: meta-llama/Llama-3.1-8B-Instruct | ||
| criticality: Critical | ||
| poolRef: | ||
| name: vllm-llama3-8b-instruct |
62 changes: 62 additions & 0 deletions
62
config/manifests/regression-testing/multi-lora-regression.yaml
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,62 @@ | ||
| apiVersion: apps/v1 | ||
| kind: Deployment | ||
| metadata: | ||
| labels: | ||
| app: benchmark-tool | ||
| name: benchmark-tool | ||
| spec: | ||
| replicas: 1 | ||
| selector: | ||
| matchLabels: | ||
| app: benchmark-tool | ||
| template: | ||
| metadata: | ||
| labels: | ||
| app: benchmark-tool | ||
| spec: | ||
| containers: | ||
| # Build image from this source https://github.com/AI-Hypercomputer/inference-benchmark/tree/46d638262650a1928e47699d78ab2da062d4422d | ||
| - image: '<DOCKER_IMAGE>' | ||
| imagePullPolicy: Always | ||
| name: benchmark-tool | ||
| command: | ||
| - bash | ||
| - -c | ||
| - ./latency_throughput_curve.sh | ||
| env: | ||
| - name: IP | ||
| value: '<target-ip>' | ||
| - name: REQUEST_RATES | ||
| value: '20,40,60,80,100,120,140,160,180,200' | ||
| - name: BENCHMARK_TIME_SECONDS | ||
| value: '300' | ||
| - name: TOKENIZER | ||
| value: 'meta-llama/Llama-3.1-8B-Instruct' | ||
| - name: MODELS | ||
| value: 'adapter-0,adapter-1,adapter-2,adapter-3,adapter-4,adapter-5,adapter-6,adapter-7,adapter-8,adapter-9,adapter-10,adapter-11,adapter-12,adapter-13,adapter-14' | ||
| - name: TRAFFIC_SPLIT | ||
| value: '0.12,0.12,0.12,0.12,0.12,0.06,0.06,0.06,0.06,0.06,0.02,0.02,0.02,0.02,0.02' | ||
| - name: BACKEND | ||
| value: vllm | ||
| - name: PORT | ||
| value: "80" | ||
| - name: INPUT_LENGTH | ||
| value: "1024" | ||
| - name: OUTPUT_LENGTH | ||
| value: '1024' | ||
| - name: FILE_PREFIX | ||
| value: benchmark | ||
| - name: PROMPT_DATASET_FILE | ||
| value: Infinity-Instruct_conversations.json | ||
| - name: HF_TOKEN | ||
| valueFrom: | ||
| secretKeyRef: | ||
| key: token | ||
| name: hf-token | ||
| resources: | ||
| limits: | ||
| cpu: "2" | ||
| memory: 20Gi | ||
| requests: | ||
| cpu: "2" | ||
| memory: 20Gi | ||
60 changes: 60 additions & 0 deletions
60
config/manifests/regression-testing/single-workload-regression.yaml
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,60 @@ | ||
| apiVersion: apps/v1 | ||
| kind: Deployment | ||
| metadata: | ||
| labels: | ||
| app: benchmark-tool | ||
| name: benchmark-tool | ||
| spec: | ||
| replicas: 1 | ||
| selector: | ||
| matchLabels: | ||
| app: benchmark-tool | ||
| template: | ||
| metadata: | ||
| labels: | ||
| app: benchmark-tool | ||
| spec: | ||
| containers: | ||
| # Build image from this source https://github.com/AI-Hypercomputer/inference-benchmark/tree/46d638262650a1928e47699d78ab2da062d4422d | ||
| - image: '<DOCKER_IMAGE>' | ||
| imagePullPolicy: Always | ||
| name: benchmark-tool | ||
| command: | ||
| - bash | ||
| - -c | ||
| - ./latency_throughput_curve.sh | ||
| env: | ||
| - name: IP | ||
| value: '<target-ip>' | ||
| - name: REQUEST_RATES | ||
| value: '300,310,320,330,340,350' | ||
| - name: BENCHMARK_TIME_SECONDS | ||
| value: '300' | ||
| - name: TOKENIZER | ||
| value: 'meta-llama/Llama-3.1-8B-Instruct' | ||
| - name: MODELS | ||
| value: 'meta-llama/Llama-3.1-8B-Instruct' | ||
| - name: BACKEND | ||
| value: vllm | ||
| - name: PORT | ||
| value: "80" | ||
| - name: INPUT_LENGTH | ||
| value: "1024" | ||
| - name: OUTPUT_LENGTH | ||
| value: '1024' | ||
| - name: FILE_PREFIX | ||
| value: benchmark | ||
| - name: PROMPT_DATASET_FILE | ||
| value: billsum_conversations.json | ||
| - name: HF_TOKEN | ||
| valueFrom: | ||
| secretKeyRef: | ||
| key: token | ||
| name: hf-token | ||
| resources: | ||
| limits: | ||
| cpu: "2" | ||
| memory: 20Gi | ||
| requests: | ||
| cpu: "2" | ||
| memory: 20Gi |
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is the file that's generated by the
import_datasets.py? We will need to build this file to the lpg image in order to use it, right? Can we provide an lpg image with the datasets built-in?Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I thought about it but both these datasets require users to sign in to hf to accept an agreement. So I did not put it in the public image. We can have it internally though
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
OK, got it, then please replace the image with a placeholder <lpg_image>, and explain how to build a new image with this dataset.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
added, it seems easier is to make update to the LPG script and point to that here. Pushed my changes to import datasets and create a docker image in the LPG repo. Please try it out.