feat: refactors, added new extraEnvVar, extraEnvFrom, `runtimeCla…

…ssName` and `podTemplate` for Model CRD, fixes (#18) - Refactored controller with new wrappers and utilities - Fixed curl not working in the container - Added new fields `extraEnvVar`, `extraEnvFrom`, `runtimeClassName` and `podTemplate` for Model CRD Close #15, #16, #17 Signed-off-by: Neko Ayaka <[email protected]>
nekomeowww · Nov 9, 2024 · daf69f3 · daf69f3
1 parent 2717e82
commit daf69f3
Show file tree

Hide file tree

Showing 10 changed files with 8,200 additions and 128 deletions.
diff --git a/README.md b/README.md
@@ -145,34 +145,8 @@ Unlock the abilities to run the following models with the Ollama Operator over K
 
 > [!TIP]
 > By the power of [`Modelfile`](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) backed by Ollama, you can create and bundle any of your own model. **As long as it's a GGUF formatted model.**
-
-| Model                                                              | Parameters | Size  | Model image         | Full model image URL                           | Multi-modal | Uncensored |
-| ------------------------------------------------------------------ | ---------- | ----- | ------------------- | ---------------------------------------------- | ----------- | ---------- |
-| [Phi-3 Mini](https://ollama.com/library/phi3)                      | 3.8B       | 2.3GB | `phi3`              | `registry.ollama.ai/library/phi3`              |             |            |
-| [Llama 3](https://ollama.com/library/llama3)                       | 8B         | 4.7GB | `llama3`            | `registry.ollama.ai/library/llama3`            |             |            |
-| [Dolphin Llama 3](https://ollama.com/library/dolphin-llama3)       | 8B         | 4.7GB | `dolphin-llama3`    | `registry.ollama.ai/dolphin-llama3`            |             | ✅          |
-| [WizardLM-2](https://ollama.com/library/wizardlm2)                 | 7B         | 4.1GB | `wizardlm2`         | `registry.ollama.ai/library/wizardlm2`         |             |            |
-| [Llama 2](https://ollama.com/library/llama2)                       | 7B         | 3.8GB | `llama2`            | `registry.ollama.ai/library/llama2`            |             |            |
-| [Mistral](https://ollama.com/library/mistral)                      | 7B         | 4.1GB | `mistral`           | `registry.ollama.ai/library/mistral`           |             |            |
-| [Mixtral 8x7B](https://ollama.com/library/mixtral:8x7b)            | 8x7B       | 26GB  | `mixtral:8x7b`      | `registry.ollama.ai/library/mixtral:8x7b`      |             |            |
-| [Mixtral 8x22B](https://ollama.com/library/mixtral:8x22b)          | 8x22B      | 80GB  | `mixtral:8x22b`     | `registry.ollama.ai/library/mixtral:8x22b`     |             |            |
-| [Command R](https://ollama.com/library/command-r)                  | 35B        | 20GB  | `command-r`         | `registry.ollama.ai/library/command-r`         |             |            |
-| [Command R Plus](https://ollama.com/library/command-r-plus)        | 104B       | 59GB  | `command-r-plus`    | `registry.ollama.ai/library/command-r-plus`    |             |            |
-| [Dolphin Phi](https://ollama.com/library/dolphin-phi)              | 2.7B       | 1.6GB | `dolphin-phi`       | `registry.ollama.ai/library/dolphin-phi`       |             | ✅          |
-| [Phi-2](https://ollama.com/library/phi)                            | 2.7B       | 1.7GB | `phi`               | `registry.ollama.ai/library/phi`               |             |            |
-| [Neural Chat](https://ollama.com/library/neural-chat)              | 7B         | 4.1GB | `neural-chat`       | `registry.ollama.ai/library/neural-chat`       |             |            |
-| [Starling](https://ollama.com/library/starling-lm)                 | 7B         | 4.1GB | `starling-lm`       | `registry.ollama.ai/library/starling-lm`       |             |            |
-| [Code Llama](https://ollama.com/library/codellama)                 | 7B         | 3.8GB | `codellama`         | `registry.ollama.ai/library/codellama`         |             |            |
-| [Llama 2 Uncensored](https://ollama.com/library/llama2-uncensored) | 7B         | 3.8GB | `llama2-uncensored` | `registry.ollama.ai/library/llama2-uncensored` |             | ✅          |
-| [Llama 2 13B](https://ollama.com/library/llama2)                   | 13B        | 7.3GB | `llama2:13b`        | `registry.ollama.ai/library/llama2:13b`        |             |            |
-| [Llama 2 70B](https://ollama.com/library/llama2)                   | 70B        | 39GB  | `llama2:70b`        | `registry.ollama.ai/library/llama2:70b`        |             |            |
-| Orca Mini                                                          | 3B         | 1.9GB | `orca-mini`         | `registry.ollama.ai/library/orca-mini`         |             |            |
-| Vicuna                                                             | 7B         | 3.8GB | `vicuna`            | `registry.ollama.ai/library/vicuna`            |             |            |
-| LLaVA                                                              | 7B         | 4.5GB | `llava`             | `registry.ollama.ai/library/llava`             | ✅           |            |
-| Gemma 2B                                                           | 2B         | 1.4GB | `gemma:2b`          | `registry.ollama.ai/library/gemma:2b`          |             |            |
-| Gemma 7B                                                           | 7B         | 4.8GB | `gemma:7b`          | `registry.ollama.ai/library/gemma:7b`          |             |            |
-
-Full list of available images can be found at [Ollama Library](https://ollama.com/library).
+>
+> Full list of available images can be found at [Ollama Library](https://ollama.com/library).
 
 > [!WARNING]
 > You should have at least 8 GB of RAM available on your node to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models.

diff --git a/api/ollama/v1/model_types.go b/api/ollama/v1/model_types.go
@@ -78,6 +78,30 @@ type ModelSpec struct {
 	// More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistent-volumes
 	// +optional
 	PersistentVolume *ModelPersistentVolumeSpec `json:"persistentVolume,omitempty" protobuf:"bytes,8,opt,name=persistentVolume"`
+	// RuntimeClassName refers to a RuntimeClass object in the node.k8s.io group, which should be used
+	// to run this pod.  If no RuntimeClass resource matches the named class, the pod will not be run.
+	// If unset or empty, the "legacy" RuntimeClass will be used, which is an implicit class with an
+	// empty definition that uses the default runtime handler.
+	// More info: https://git.k8s.io/enhancements/keps/sig-node/585-runtime-class
+	// +optional
+	RuntimeClassName *string `json:"runtimeClassName,omitempty" protobuf:"bytes,9,opt,name=runtimeClassName"`
+	// List of sources to populate environment variables in the container.
+	// The keys defined within a source must be a C_IDENTIFIER. All invalid keys
+	// will be reported as an event when the container is starting. When a key exists in multiple
+	// sources, the value associated with the last source will take precedence.
+	// Values defined by an Env with a duplicate key will take precedence.
+	// Cannot be updated.
+	// +optional
+	ExtraEnvFrom []corev1.EnvFromSource `json:"extraEnvFrom,omitempty" protobuf:"bytes,10,rep,name=extraEnvFrom"`
+	// List of environment variables to set in the container.
+	// Cannot be updated.
+	// +optional
+	// +patchMergeKey=name
+	// +patchStrategy=merge
+	Env []corev1.EnvVar `json:"extraEnv,omitempty" patchStrategy:"merge" patchMergeKey:"name" protobuf:"bytes,11,rep,name=extraEnv"`
+	// PodTemplateSpec describes the data a pod should have when created from a template
+	// +optional
+	PodTemplate *corev1.PodTemplateSpec `json:"podTemplate" protobuf:"bytes,12,opt,name=podTemplate"`
 }
 
 type ConditionType string