From ae4e1a0423e27fe368adf7bdc323cc82fddbd641 Mon Sep 17 00:00:00 2001 From: Fei-Guo Date: Fri, 10 Jan 2025 11:58:37 -0800 Subject: [PATCH] docs: Update to use Standard_NC24ads_A100_v4 as default SKU in docs --- README.md | 6 +++--- .../custom-deployment-template.yaml | 2 +- .../reference-image-deployment.yaml | 4 ++-- docs/inference/README.md | 6 +++--- examples/inference/kaito_workspace_falcon_7b-instruct.yaml | 2 +- examples/inference/kaito_workspace_falcon_7b.yaml | 4 ++-- .../inference/kaito_workspace_falcon_7b_with_adapters.yaml | 4 ++-- examples/inference/kaito_workspace_llama2_13b-chat.yaml | 2 +- examples/inference/kaito_workspace_llama2_13b.yaml | 2 +- examples/inference/kaito_workspace_llama2_7b-chat.yaml | 2 +- examples/inference/kaito_workspace_llama2_7b.yaml | 2 +- examples/inference/kaito_workspace_mistral_7b-instruct.yaml | 2 +- examples/inference/kaito_workspace_mistral_7b.yaml | 2 +- examples/inference/kaito_workspace_phi_2.yaml | 2 +- examples/inference/kaito_workspace_phi_3.5-instruct.yaml | 2 +- examples/inference/kaito_workspace_phi_3_mini_128k.yaml | 2 +- examples/inference/kaito_workspace_phi_3_mini_4k.yaml | 2 +- examples/inference/kaito_workspace_phi_3_with_adapters.yaml | 2 +- 18 files changed, 25 insertions(+), 25 deletions(-) diff --git a/README.md b/README.md index 86cd0dcd4..54d208fab 100644 --- a/README.md +++ b/README.md @@ -50,7 +50,7 @@ kind: Workspace metadata: name: workspace-phi-3-5-mini resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: phi-3-5 @@ -65,8 +65,8 @@ The workspace status can be tracked by running the following command. When the W ```sh $ kubectl get workspace workspace-phi-3-5-mini -NAME INSTANCE RESOURCEREADY INFERENCEREADY JOBSTARTED WORKSPACESUCCEEDED AGE -workspace-phi-3-5-mini Standard_NC6s_v3 True True True 4h15m +NAME INSTANCE RESOURCEREADY INFERENCEREADY JOBSTARTED WORKSPACESUCCEEDED AGE +workspace-phi-3-5-mini Standard_NC24ads_A100_v4 True True True 4h15m ``` Next, one can find the inference service's cluster ip and use a temporal `curl` pod to test the service endpoint in the cluster. diff --git a/docs/custom-model-integration/custom-deployment-template.yaml b/docs/custom-model-integration/custom-deployment-template.yaml index 999e81c07..fe9c2c4ad 100644 --- a/docs/custom-model-integration/custom-deployment-template.yaml +++ b/docs/custom-model-integration/custom-deployment-template.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-custom-llm resource: - instanceType: "Standard_NC12s_v3" # Replace with the required VM SKU based on model requirements + instanceType: "Standard_NC24ads_A100_v4" # Replace with the required VM SKU based on model requirements labelSelector: matchLabels: apps: custom-llm diff --git a/docs/custom-model-integration/reference-image-deployment.yaml b/docs/custom-model-integration/reference-image-deployment.yaml index c3bb75171..3a77dba08 100644 --- a/docs/custom-model-integration/reference-image-deployment.yaml +++ b/docs/custom-model-integration/reference-image-deployment.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-custom-llm resource: - instanceType: "Standard_NC12s_v3" # Replace with the required VM SKU based on model requirements + instanceType: "Standard_NC24ads_A100_v4" # Replace with the required VM SKU based on model requirements labelSelector: matchLabels: apps: custom-llm @@ -37,4 +37,4 @@ inference: volumes: - name: dshm emptyDir: - medium: Memory \ No newline at end of file + medium: Memory diff --git a/docs/inference/README.md b/docs/inference/README.md index bf28ef835..765012f5d 100644 --- a/docs/inference/README.md +++ b/docs/inference/README.md @@ -12,7 +12,7 @@ kind: Workspace metadata: name: workspace-falcon-7b resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: falcon-7b @@ -54,7 +54,7 @@ metadata: annotations: kaito.sh/runtime: "transformers" resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: falcon-7b @@ -73,7 +73,7 @@ kind: Workspace metadata: name: workspace-falcon-7b resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: falcon-7b diff --git a/examples/inference/kaito_workspace_falcon_7b-instruct.yaml b/examples/inference/kaito_workspace_falcon_7b-instruct.yaml index 95c807b79..80188c2db 100644 --- a/examples/inference/kaito_workspace_falcon_7b-instruct.yaml +++ b/examples/inference/kaito_workspace_falcon_7b-instruct.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-falcon-7b-instruct resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: falcon-7b-instruct diff --git a/examples/inference/kaito_workspace_falcon_7b.yaml b/examples/inference/kaito_workspace_falcon_7b.yaml index afb813757..b5531f678 100644 --- a/examples/inference/kaito_workspace_falcon_7b.yaml +++ b/examples/inference/kaito_workspace_falcon_7b.yaml @@ -3,11 +3,11 @@ kind: Workspace metadata: name: workspace-falcon-7b resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: falcon-7b inference: preset: name: "falcon-7b" - \ No newline at end of file + diff --git a/examples/inference/kaito_workspace_falcon_7b_with_adapters.yaml b/examples/inference/kaito_workspace_falcon_7b_with_adapters.yaml index e2ce58dec..f62b1b7a3 100644 --- a/examples/inference/kaito_workspace_falcon_7b_with_adapters.yaml +++ b/examples/inference/kaito_workspace_falcon_7b_with_adapters.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-falcon-7b resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: falcon-7b @@ -15,4 +15,4 @@ inference: name: "falcon-7b-adapter" image: "" strength: "0.2" - \ No newline at end of file + diff --git a/examples/inference/kaito_workspace_llama2_13b-chat.yaml b/examples/inference/kaito_workspace_llama2_13b-chat.yaml index 45c8a3b57..042547ee8 100644 --- a/examples/inference/kaito_workspace_llama2_13b-chat.yaml +++ b/examples/inference/kaito_workspace_llama2_13b-chat.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-llama-2-13b-chat resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: llama-2-13b-chat diff --git a/examples/inference/kaito_workspace_llama2_13b.yaml b/examples/inference/kaito_workspace_llama2_13b.yaml index 8a0923cd6..8dec0dbe3 100644 --- a/examples/inference/kaito_workspace_llama2_13b.yaml +++ b/examples/inference/kaito_workspace_llama2_13b.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-llama-2-13b resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: llama-2-13b diff --git a/examples/inference/kaito_workspace_llama2_7b-chat.yaml b/examples/inference/kaito_workspace_llama2_7b-chat.yaml index b1c68544a..d16d5a089 100644 --- a/examples/inference/kaito_workspace_llama2_7b-chat.yaml +++ b/examples/inference/kaito_workspace_llama2_7b-chat.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-llama-2-7b-chat resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: llama-2-7b-chat diff --git a/examples/inference/kaito_workspace_llama2_7b.yaml b/examples/inference/kaito_workspace_llama2_7b.yaml index ba72eb3eb..63536c5c8 100644 --- a/examples/inference/kaito_workspace_llama2_7b.yaml +++ b/examples/inference/kaito_workspace_llama2_7b.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-llama-2-7b resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: llama-2-7b diff --git a/examples/inference/kaito_workspace_mistral_7b-instruct.yaml b/examples/inference/kaito_workspace_mistral_7b-instruct.yaml index 6a7539d09..1d1134978 100644 --- a/examples/inference/kaito_workspace_mistral_7b-instruct.yaml +++ b/examples/inference/kaito_workspace_mistral_7b-instruct.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-mistral-7b-instruct resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: mistral-7b-instruct diff --git a/examples/inference/kaito_workspace_mistral_7b.yaml b/examples/inference/kaito_workspace_mistral_7b.yaml index 47f69c995..59b86acad 100644 --- a/examples/inference/kaito_workspace_mistral_7b.yaml +++ b/examples/inference/kaito_workspace_mistral_7b.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-mistral-7b resource: - instanceType: "Standard_NC12s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: mistral-7b diff --git a/examples/inference/kaito_workspace_phi_2.yaml b/examples/inference/kaito_workspace_phi_2.yaml index d1bb49eea..3310b82b7 100644 --- a/examples/inference/kaito_workspace_phi_2.yaml +++ b/examples/inference/kaito_workspace_phi_2.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-phi-2 resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: phi-2 diff --git a/examples/inference/kaito_workspace_phi_3.5-instruct.yaml b/examples/inference/kaito_workspace_phi_3.5-instruct.yaml index 4c2497fe3..da17357c0 100644 --- a/examples/inference/kaito_workspace_phi_3.5-instruct.yaml +++ b/examples/inference/kaito_workspace_phi_3.5-instruct.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-phi-3-5-mini resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: phi-3-5 diff --git a/examples/inference/kaito_workspace_phi_3_mini_128k.yaml b/examples/inference/kaito_workspace_phi_3_mini_128k.yaml index 162495ef8..af85d80d2 100644 --- a/examples/inference/kaito_workspace_phi_3_mini_128k.yaml +++ b/examples/inference/kaito_workspace_phi_3_mini_128k.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-phi-3-mini resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: phi-3 diff --git a/examples/inference/kaito_workspace_phi_3_mini_4k.yaml b/examples/inference/kaito_workspace_phi_3_mini_4k.yaml index 33cd49d68..151feb094 100644 --- a/examples/inference/kaito_workspace_phi_3_mini_4k.yaml +++ b/examples/inference/kaito_workspace_phi_3_mini_4k.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-phi-3-mini resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: phi-3 diff --git a/examples/inference/kaito_workspace_phi_3_with_adapters.yaml b/examples/inference/kaito_workspace_phi_3_with_adapters.yaml index 8dd754c48..69edb4692 100644 --- a/examples/inference/kaito_workspace_phi_3_with_adapters.yaml +++ b/examples/inference/kaito_workspace_phi_3_with_adapters.yaml @@ -3,7 +3,7 @@ kind: Workspace metadata: name: workspace-phi-3-mini-adapter resource: - instanceType: "Standard_NC6s_v3" + instanceType: "Standard_NC24ads_A100_v4" labelSelector: matchLabels: apps: phi-3-adapter