feat: Add DeepSeek READMEs and Example (#851)

**Reason for Change**: Add DeepSeek READMEs and Example
kaito-project · Jan 30, 2025 · e333f2a · e333f2a
1 parent 31bdf47
commit e333f2a
Show file tree

Hide file tree

Showing 3 changed files with 39 additions and 0 deletions.
diff --git a/examples/inference/kaito_workspace_deepseek_r1_distill_llama_8b.yaml b/examples/inference/kaito_workspace_deepseek_r1_distill_llama_8b.yaml
@@ -0,0 +1,13 @@
+apiVersion: kaito.sh/v1alpha1
+kind: Workspace
+metadata:
+  name: workspace-deepseek-r1-distill-llama-8b
+resource:
+  instanceType: "Standard_NC24ads_A100_v4"
+  labelSelector:
+    matchLabels:
+      apps: deepseek-r1-distill-llama-8b
+inference:
+  preset:
+    name: "deepseek-r1-distill-llama-8b"
+
diff --git a/examples/inference/kaito_workspace_deepseek_r1_distill_qwen_14b.yaml b/examples/inference/kaito_workspace_deepseek_r1_distill_qwen_14b.yaml
@@ -0,0 +1,13 @@
+apiVersion: kaito.sh/v1alpha1
+kind: Workspace
+metadata:
+  name: workspace-deepseek-r1-distill-qwen-14b
+resource:
+  instanceType: "Standard_NC24ads_A100_v4"
+  labelSelector:
+    matchLabels:
+      apps: deepseek-r1-distill-qwen-14b
+inference:
+  preset:
+    name: "deepseek-r1-distill-qwen-14b"
+
diff --git a/presets/workspace/models/deepseek/README.md b/presets/workspace/models/deepseek/README.md
@@ -0,0 +1,13 @@
+## Supported Models
+| Model name          |                        Model source                         |                                      | Kubernetes Workload | Distributed inference |
+|---------------------|:-----------------------------------------------------------:|:-------------------------------------------------------------------------------:|:-------------------:|:---------------------:|
+| deepseek-r1-distill-llama-8b  | [deepseek-r1-distill-llama-8b](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B)  | [link](../../../../examples/inference/kaito_workspace_deepseek_r1_distill_llama_8b.yaml)  |     Deployment      |         false         |
+| deepseek-r1-distill-qwen-14b  | [deepseek-r1-distill-qwen-14b](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)  | [link](../../../../examples/inference/kaito_workspace_deepseek_r1_distill_qwen_14b.yaml)  |     Deployment      |         false         |
+
+
+## Image Source
+- **Public**: Kaito maintainers manage the lifecycle of the inference service images that contain model weights. The images are available in Microsoft Container Registry (MCR).
+
+## Usage
+
+See [document](../../../../docs/inference/README.md).