[CLEANUP]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms-cloud"
-version = "0.2.4"
+version = "0.2.5"
 description = "Swarms Cloud - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <[email protected]>"]
@@ -35,7 +35,6 @@ sse-starlette = "2.0.0"
 uvicorn = "*"
 shortuuid = "*"
 xformers = "*"
-exxa = "*"
 
 [tool.poetry.group.lint.dependencies]
 ruff = ">=0.1.6,<0.4.0"

servers/text_to_video/sky_serve.yaml

@@ -0,0 +1,118 @@
+envs:
+  MODEL_NAME: mistralai/Mixtral-8x7B-Instruct-v0.1
+  HF_HUB_ENABLE_HF_TRANSFER: True
+
+
+# service.yaml
+service:
+  # An actual request for readiness probe.
+  readiness_probe:
+    path: /v1/chat/completions
+    post_data:
+      model: $MODEL_NAME
+      messages:
+        - role: user
+          content: Hello! What is your name?
+      max_tokens: 1
+  readiness_probe: /health
+  readiness_probe: /v1/models
+  replica_policy:
+    min_replicas: 2
+    max_replicas: 10
+    target_qps_per_replica: 2.5
+    upscale_delay_seconds: 300
+    downscale_delay_seconds: 1200
+
+# # # Advanced Kubernetes configurations (optional).
+# kubernetes:
+#   # The networking mode for accessing SSH jump pod (optional).
+#   #
+#   # This must be either: 'nodeport' or 'portforward'. If not specified,
+#   # defaults to 'portforward'.
+
+#   #
+#   # nodeport: Exposes the jump pod SSH service on a static port number on each
+#   # Node, allowing external access to using <NodeIP>:<NodePort>. Using this
+#   # mode requires opening multiple ports on nodes in the Kubernetes cluster.
+#   #
+#   # portforward: Uses `kubectl port-forward` to create a tunnel and directly
+#   # access the jump pod SSH service in the Kubernetes cluster. Does not
+#   # require opening ports the cluster nodes and is more secure. 'portforward'
+#   # is used as default if 'networking' is not specified.
+#   networking: portforward
+
+#   # The mode to use for opening ports on Kubernetes
+#   #
+#   # This must be either: 'ingress' or 'loadbalancer'. If not specified,
+#   # defaults to 'loadbalancer'.
+#   #
+#   # loadbalancer: Creates services of type `LoadBalancer` to expose ports.
+#   # See https://skypilot.readthedocs.io/en/latest/reference/kubernetes/kubernetes-setup.html#loadbalancer-service.
+#   # This mode is supported out of the box on most cloud managed Kubernetes
+#   # environments (e.g., GKE, EKS).
+#   #
+#   # ingress: Creates an ingress and a ClusterIP service for each port opened.
+#   # Requires an Nginx ingress controller to be configured on the Kubernetes cluster.
+#   # Refer to https://skypilot.readthedocs.io/en/latest/reference/kubernetes/kubernetes-setup.html#nginx-ingress
+#   # for details on deploying the NGINX ingress controller.
+#   ports: loadbalancer
+
+#   # Attach custom metadata to Kubernetes objects created by SkyPilot
+#   #
+#   # Uses the same schema as Kubernetes metadata object: https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.26/#objectmeta-v1-meta
+#   #
+#   # Since metadata is applied to all all objects created by SkyPilot,
+#   # specifying 'name' and 'namespace' fields here is not allowed.
+#   # custom_metadata:
+#   #   labels:
+#   #     mylabel: myvalue
+#   #   annotations:
+#   #     myannotation: myvalue
+
+#   # Additional fields to override the pod fields used by SkyPilot (optional)
+#   #
+#   # Any key:value pairs added here would get added to the pod spec used to
+#   # create SkyPilot pods. The schema follows the same schema for a Pod object
+#   # in the Kubernetes API:
+#   # https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.26/#pod-v1-core
+#   #
+#   # # Some example use cases are shown below. All fields are optional.
+#   # pod_config:
+#   #   spec:
+#   #     runtimeClassName: nvidia    # Custom runtimeClassName for GPU pods.
+#   #     containers:
+#   #       - env:                # Custom environment variables for the pod, e.g., for proxy
+#   #         - name: HTTP_PROXY
+#   #           value: http://proxy-host:3128
+#   #         volumeMounts:       # Custom volume mounts for the pod
+#   #           - mountPath: /foo
+#   #             name: swarms
+#   #             readOnly: true
+#   #     volumes:
+#   #       - name: swarms
+#   #         hostPath:
+#   #           path: /tmp
+#   #           type: Directory
+#   #       - name: swarms          # Use this to modify the /dev/shm volume mounted by SkyPilot
+#   #         emptyDir:
+#   #           medium: Memory
+#   #           sizeLimit: 3Gi    # Set a size limit for the /dev/shm volume
+
+
+# Fields below describe each replica.
+resources:
+  accelerators: {L4:8, A10g:8, A100:4, A100:8, A100-80GB:2, A100-80GB:4, A100-80GB:8}
+  # cpus: 32+
+  # memory: 512+
+  # use_spot: True
+  # disk_size: 512  # Ensure model checkpoints (~246GB) can fit.
+  # disk_tier: best
+  ports: 8000  # Expose to internet traffic.
+
+# workdir: ~/swarms-cloud/servers/cogvlm
+
+setup: |
+  docker build -t ttv .
+
+run: |
+  docker run ttv