chore: import upstream snapshot with attribution

doc/source/templates/testing/cluster_envs/02_many_model_training.yaml

@@ -0,0 +1,16 @@
+base_image: anyscale/ray-ml:nightly-py39-gpu
+env_vars: {}
+
+post_build_cmds:
+  # Install Ray
+  - pip3 uninstall -y ray || true && pip3 install -U {{ env["RAY_WHEELS"] | default("ray") }}
+  - {{ env["RAY_WHEELS_SANITY_CHECK"] | default("echo No Ray wheels sanity check") }}
+
+python:
+  pip_packages:
+    - statsforecast==1.5.0
+    # numba doesn't support numpy > 1.24
+    # See: https://github.com/numba/numba/issues/8698
+    # NOTE: This is only an issue when `statsforecast` is installed with
+    # `pip install -U`, which is what's happening for this cluster env.
+    - numpy<1.25.0

doc/source/templates/testing/cluster_envs/03_serving_stable_diffusion.yaml

@@ -0,0 +1,20 @@
+base_image: anyscale/ray:nightly-py39-cu118
+
+debian_packages:
+  - curl
+
+post_build_cmds:
+  # Install Ray
+  - pip3 uninstall -y ray || true && pip3 install -U {{ env["RAY_WHEELS"] | default("ray") }}
+  - {{ env["RAY_WHEELS_SANITY_CHECK"] | default("echo No Ray wheels sanity check") }}
+
+python:
+  pip_packages:
+    - accelerate==0.20.3
+    - diffusers==0.17.1
+    - fastapi==0.97.0
+    - ipywidgets
+    - matplotlib==3.7.1
+    - numpy==1.24.3
+    - torch==2.0.1
+    - transformers==4.30.1

doc/source/templates/testing/cluster_envs/04_finetuning_llms_with_deepspeed.yaml

@@ -0,0 +1,33 @@
+base_image: anyscale/ray:nightly-py39-cu118
+
+env_vars: {}
+
+debian_packages:
+  - libaio1
+
+python:
+  pip_packages: [
+    peft==0.7.0,
+    deepspeed,
+    fairscale,
+    transformers>=4.31.0,
+    dataset,
+    accelerate,
+    evaluate,
+    bitsandbytes,
+    wandb,
+    pytorch-lightning,
+    protobuf,
+    torchmetrics,
+    lm_eval==0.3.0,
+    tiktoken==0.1.2,
+    sentencepiece,
+  ]
+  conda_packages: []
+
+post_build_cmds:
+  - pip uninstall bitsandbytes -y || true
+  - pip install torch==2.1.1 --index-url https://download.pytorch.org/whl/cu118
+  # Install Ray
+  - pip3 uninstall -y ray || true && pip3 install -U {{ env["RAY_WHEELS"] | default("ray") }}
+  - {{ env["RAY_WHEELS_SANITY_CHECK"] | default("echo No Ray wheels sanity check") }}

doc/source/templates/testing/cluster_envs/default_cluster_env_nightly_ml_py39.yaml

@@ -0,0 +1,9 @@
+base_image: anyscale/ray-ml:nightly-py39-gpu
+env_vars: {}
+debian_packages:
+  - curl
+
+post_build_cmds:
+  # Install Ray
+  - pip3 uninstall -y ray || true && pip3 install -U {{ env["RAY_WHEELS"] | default("ray") }}
+  - {{ env["RAY_WHEELS_SANITY_CHECK"] | default("echo No Ray wheels sanity check") }}

doc/source/templates/testing/compute_configs/04_finetuning_llms_with_deepspeed/aws_70b_v1.yaml

@@ -0,0 +1,23 @@
+cloud_id: {{env["ANYSCALE_CLOUD_ID"]}}
+region: us-west-2
+
+head_node_type:
+  name: head_node_type
+  instance_type: g5.48xlarge
+  resources:
+    custom_resources:
+      large_cpu_mem: 1
+
+worker_node_types:
+  - name: gpu_worker
+    instance_type: g5.48xlarge
+    min_workers: 3
+    max_workers: 3
+    use_spot: false
+
+advanced_configurations_json:
+  TagSpecifications:
+    - ResourceType: "instance"
+      Tags:
+        - Key: ttl-hours
+          Value: '24'

doc/source/templates/testing/compute_configs/04_finetuning_llms_with_deepspeed/aws_70b_v2.yaml

@@ -0,0 +1,29 @@
+cloud_id: {{env["ANYSCALE_CLOUD_ID"]}}
+region: us-west-2
+
+head_node_type:
+  name: head_node_type
+  instance_type: g5.48xlarge
+  resources:
+    custom_resources:
+      large_cpu_mem: 1
+
+worker_node_types:
+  - name: large_gpu_worker
+    instance_type: g5.48xlarge
+    min_workers: 2
+    max_workers: 2
+    use_spot: false
+
+  - name: medium_gpu_worker
+    instance_type: g5.24xlarge
+    min_workers: 2
+    max_workers: 2
+    use_spot: false
+
+advanced_configurations_json:
+  TagSpecifications:
+    - ResourceType: "instance"
+      Tags:
+        - Key: ttl-hours
+          Value: '24'

doc/source/templates/testing/compute_configs/04_finetuning_llms_with_deepspeed/aws_7b.yaml

@@ -0,0 +1,21 @@
+# Autoscale to 16 g5.4xlarge --> 16 A10Gs
+cloud_id: {{env["ANYSCALE_CLOUD_ID"]}}
+region: us-west-2
+
+head_node_type:
+    name: head_node
+    instance_type: m5.xlarge
+
+worker_node_types:
+    - name: worker_node
+      instance_type: g5.4xlarge
+      min_workers: 0
+      max_workers: 16
+      use_spot: false
+
+advanced_configurations_json:
+  TagSpecifications:
+    - ResourceType: "instance"
+      Tags:
+        - Key: ttl-hours
+          Value: '24'

doc/source/templates/testing/compute_configs/04_finetuning_llms_with_deepspeed/gce_7b.yaml

@@ -0,0 +1,16 @@
+cloud_id: {{env["ANYSCALE_CLOUD_ID"]}}
+region: us-west1
+allowed_azs:
+    - us-west1-b
+
+head_node_type:
+  name: head_node_type
+  instance_type: n2-standard-16
+
+worker_node_types:
+- name: gpu_worker
+  instance_type: g2-standard-16-nvidia-l4-1
+  min_workers: 0
+  max_workers: 16
+  use_spot: false
+

doc/source/templates/testing/compute_configs/cpu/aws.yaml

@@ -0,0 +1,21 @@
+cloud_id: {{ env["ANYSCALE_CLOUD_ID"] }}
+region: us-west-2
+
+# 8 m5.2xlarge nodes --> 64 CPUs
+head_node_type:
+  name: head_node_type
+  instance_type: m5.2xlarge
+
+worker_node_types:
+- name: cpu_worker
+  instance_type: m5.2xlarge
+  min_workers: 7
+  max_workers: 7
+  use_spot: false
+
+advanced_configurations_json:
+  TagSpecifications:
+    - ResourceType: "instance"
+      Tags:
+        - Key: ttl-hours
+          Value: '24'

doc/source/templates/testing/compute_configs/cpu/gce.yaml

@@ -0,0 +1,17 @@
+cloud_id: {{ env["ANYSCALE_CLOUD_ID"] }}
+
+region: us-west1
+allowed_azs:
+    - us-west1-b
+
+# 8 n2-standard-8 nodes --> 64 CPUs
+head_node_type:
+  name: head_node_type
+  instance_type: n2-standard-8
+
+worker_node_types:
+- name: cpu_worker
+  instance_type: n2-standard-8
+  min_workers: 7
+  max_workers: 7
+  use_spot: false

doc/source/templates/testing/compute_configs/gpu/aws.yaml

@@ -0,0 +1,21 @@
+cloud_id: {{ env["ANYSCALE_CLOUD_ID"] }}
+region: us-west-2
+
+# 4 g4dn.2xlarge nodes --> 32 CPUs, 4 GPUs
+head_node_type:
+  name: head_node_type
+  instance_type: g4dn.2xlarge
+
+worker_node_types:
+- name: gpu_worker
+  instance_type: g4dn.2xlarge
+  min_workers: 3
+  max_workers: 3
+  use_spot: false
+
+advanced_configurations_json:
+  TagSpecifications:
+    - ResourceType: "instance"
+      Tags:
+        - Key: ttl-hours
+          Value: '24'

doc/source/templates/testing/compute_configs/gpu/gce.yaml

@@ -0,0 +1,17 @@
+cloud_id: {{ env["ANYSCALE_CLOUD_ID"] }}
+
+region: us-west1
+allowed_azs:
+    - us-west1-b
+
+# 4 n1-standard-8-nvidia-tesla-t4-1 nodes --> 32 CPUs, 4 GPUs
+head_node_type:
+  name: head_node_type
+  instance_type: n1-standard-8-nvidia-tesla-t4-1
+
+worker_node_types:
+- name: gpu_worker
+  instance_type: n1-standard-8-nvidia-tesla-t4-1
+  min_workers: 3
+  max_workers: 3
+  use_spot: false

doc/source/templates/testing/docker/03_serving_stable_diffusion/Dockerfile

@@ -0,0 +1,9 @@
+# Dockerfile used to create the docker image for `03_serving_stable_diffusion`.
+FROM anyscale/ray:latest-py39-cu118
+
+COPY requirements.txt ./
+
+RUN pip install --no-cache-dir -U -r requirements.txt
+
+RUN echo "Testing Ray Import..." && python -c "import ray"
+RUN ray --version

doc/source/templates/testing/docker/03_serving_stable_diffusion/requirements.txt

@@ -0,0 +1,8 @@
+accelerate==0.20.3
+diffusers==0.17.1
+fastapi==0.97.0
+ipywidgets
+matplotlib==3.7.1
+numpy==1.24.3
+torch==2.0.1
+transformers==4.30.1

doc/source/templates/testing/docker/04_finetuning_llms_with_deepspeed/Dockerfile

@@ -0,0 +1,17 @@
+# Dockerfile used to create the docker image for `04_finetuning_llms_with_deepspeed`.
+FROM anyscale/ray:2.9.0-py310-cu121
+
+COPY requirements.txt ./
+
+RUN sudo apt-get update
+RUN sudo apt-get install -y libaio1
+
+RUN pip install --upgrade pip
+# We need pydantic at this version to install deepspeed 0.10.2 (as part of the requirements.txt)
+RUN pip install pydantic==1.10.7
+RUN pip install -U -r requirements.txt
+RUN pip install torch==2.1.1 --index-url https://download.pytorch.org/whl/cu121
+RUN pip install flash-attn==2.4.2 --no-build-isolation
+
+RUN echo "Testing Ray Import..." && python -c "import ray"
+RUN ray --version

doc/source/templates/testing/docker/04_finetuning_llms_with_deepspeed/requirements.txt

@@ -0,0 +1,12 @@
+deepspeed==0.10.2
+fairscale
+transformers>=4.36.2
+dataset
+accelerate
+evaluate
+wandb
+pytorch-lightning
+protobuf
+torchmetrics
+sentencepiece
+peft==0.7.0