dstack 0.19.35__tar.gz → 0.19.36__tar.gz

{dstack-0.19.35 → dstack-0.19.36}/.github/workflows/release.yml

@@ -100,11 +100,17 @@ jobs:
           VERSION=${{ needs.compute-version.outputs.version }}
           docker buildx build --platform linux/arm64/v8 --build-arg VERSION=$VERSION --push --provenance=false --tag dstackai/dstack:$VERSION-arm64 -f release/Dockerfile .
           docker buildx build --platform linux/amd64 --build-arg VERSION=$VERSION --push --provenance=false --tag dstackai/dstack:$VERSION-amd64 -f release/Dockerfile .
+          docker buildx build --platform linux/arm64/v8 --build-arg BASE_IMAGE=dstackai/dstack:$VERSION-arm64 --push --provenance=false --tag dstackai/dstack:nebius-$VERSION-arm64 -f Dockerfile.nebius .
+          docker buildx build --platform linux/amd64 --build-arg BASE_IMAGE=dstackai/dstack:$VERSION-amd64 --push --provenance=false --tag dstackai/dstack:nebius-$VERSION-amd64 -f Dockerfile.nebius .
           docker manifest create dstackai/dstack:$VERSION --amend dstackai/dstack:$VERSION-arm64 --amend dstackai/dstack:$VERSION-amd64
           docker manifest push dstackai/dstack:$VERSION
+          docker manifest create dstackai/dstack:nebius-$VERSION --amend dstackai/dstack:nebius-$VERSION-arm64 --amend dstackai/dstack:nebius-$VERSION-amd64
+          docker manifest push dstackai/dstack:nebius-$VERSION
           if [ -n "${{ needs.compute-version.outputs.latest }}" ]; then
             docker manifest create dstackai/dstack:latest --amend dstackai/dstack:$VERSION-arm64 --amend dstackai/dstack:$VERSION-amd64
             docker manifest push dstackai/dstack:latest
+            docker manifest create dstackai/dstack:nebius-latest --amend dstackai/dstack:nebius-$VERSION-arm64 --amend dstackai/dstack:nebius-$VERSION-amd64
+            docker manifest push dstackai/dstack:nebius-latest
           fi
       - name: Docker Hub Description
         uses: peter-evans/dockerhub-description@v4

{dstack-0.19.35 → dstack-0.19.36}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dstack
-Version: 0.19.35
+Version: 0.19.36
 Summary: dstack is an open-source orchestration engine for running AI workloads on any cloud or on-premises.
 Project-URL: Homepage, https://dstack.ai
 Project-URL: Source, https://github.com/dstackai/dstack
@@ -22,7 +22,7 @@ Requires-Dist: cryptography
 Requires-Dist: cursor
 Requires-Dist: filelock
 Requires-Dist: gitpython
-Requires-Dist: gpuhunt==0.1.11
+Requires-Dist: gpuhunt==0.1.12
 Requires-Dist: ignore-python>=0.2.0
 Requires-Dist: jsonschema
 Requires-Dist: orjson
@@ -77,7 +77,7 @@ Requires-Dist: nebius<0.4,>=0.3.4; (python_version >= '3.10') and extra == 'all'
 Requires-Dist: oci>=2.150.0; extra == 'all'
 Requires-Dist: prometheus-client; extra == 'all'
 Requires-Dist: pyopenssl>=23.2.0; extra == 'all'
-Requires-Dist: python-dxf==12.1.0; extra == 'all'
+Requires-Dist: python-dxf>=12.1.1; extra == 'all'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'all'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'all'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'all'
@@ -102,7 +102,7 @@ Requires-Dist: grpcio>=1.50; extra == 'aws'
 Requires-Dist: httpx; extra == 'aws'
 Requires-Dist: jinja2; extra == 'aws'
 Requires-Dist: prometheus-client; extra == 'aws'
-Requires-Dist: python-dxf==12.1.0; extra == 'aws'
+Requires-Dist: python-dxf>=12.1.1; extra == 'aws'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'aws'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'aws'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'aws'
@@ -131,7 +131,7 @@ Requires-Dist: grpcio>=1.50; extra == 'azure'
 Requires-Dist: httpx; extra == 'azure'
 Requires-Dist: jinja2; extra == 'azure'
 Requires-Dist: prometheus-client; extra == 'azure'
-Requires-Dist: python-dxf==12.1.0; extra == 'azure'
+Requires-Dist: python-dxf>=12.1.1; extra == 'azure'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'azure'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'azure'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'azure'
@@ -154,7 +154,7 @@ Requires-Dist: grpcio>=1.50; extra == 'datacrunch'
 Requires-Dist: httpx; extra == 'datacrunch'
 Requires-Dist: jinja2; extra == 'datacrunch'
 Requires-Dist: prometheus-client; extra == 'datacrunch'
-Requires-Dist: python-dxf==12.1.0; extra == 'datacrunch'
+Requires-Dist: python-dxf>=12.1.1; extra == 'datacrunch'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'datacrunch'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'datacrunch'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'datacrunch'
@@ -191,7 +191,7 @@ Requires-Dist: grpcio>=1.50; extra == 'gcp'
 Requires-Dist: httpx; extra == 'gcp'
 Requires-Dist: jinja2; extra == 'gcp'
 Requires-Dist: prometheus-client; extra == 'gcp'
-Requires-Dist: python-dxf==12.1.0; extra == 'gcp'
+Requires-Dist: python-dxf>=12.1.1; extra == 'gcp'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'gcp'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'gcp'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'gcp'
@@ -214,7 +214,7 @@ Requires-Dist: httpx; extra == 'kubernetes'
 Requires-Dist: jinja2; extra == 'kubernetes'
 Requires-Dist: kubernetes; extra == 'kubernetes'
 Requires-Dist: prometheus-client; extra == 'kubernetes'
-Requires-Dist: python-dxf==12.1.0; extra == 'kubernetes'
+Requires-Dist: python-dxf>=12.1.1; extra == 'kubernetes'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'kubernetes'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'kubernetes'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'kubernetes'
@@ -238,7 +238,7 @@ Requires-Dist: grpcio>=1.50; extra == 'lambda'
 Requires-Dist: httpx; extra == 'lambda'
 Requires-Dist: jinja2; extra == 'lambda'
 Requires-Dist: prometheus-client; extra == 'lambda'
-Requires-Dist: python-dxf==12.1.0; extra == 'lambda'
+Requires-Dist: python-dxf>=12.1.1; extra == 'lambda'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'lambda'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'lambda'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'lambda'
@@ -261,7 +261,7 @@ Requires-Dist: httpx; extra == 'nebius'
 Requires-Dist: jinja2; extra == 'nebius'
 Requires-Dist: nebius<0.4,>=0.3.4; (python_version >= '3.10') and extra == 'nebius'
 Requires-Dist: prometheus-client; extra == 'nebius'
-Requires-Dist: python-dxf==12.1.0; extra == 'nebius'
+Requires-Dist: python-dxf>=12.1.1; extra == 'nebius'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'nebius'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'nebius'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'nebius'
@@ -286,7 +286,7 @@ Requires-Dist: jinja2; extra == 'oci'
 Requires-Dist: oci>=2.150.0; extra == 'oci'
 Requires-Dist: prometheus-client; extra == 'oci'
 Requires-Dist: pyopenssl>=23.2.0; extra == 'oci'
-Requires-Dist: python-dxf==12.1.0; extra == 'oci'
+Requires-Dist: python-dxf>=12.1.1; extra == 'oci'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'oci'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'oci'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'oci'
@@ -308,7 +308,7 @@ Requires-Dist: grpcio>=1.50; extra == 'server'
 Requires-Dist: httpx; extra == 'server'
 Requires-Dist: jinja2; extra == 'server'
 Requires-Dist: prometheus-client; extra == 'server'
-Requires-Dist: python-dxf==12.1.0; extra == 'server'
+Requires-Dist: python-dxf>=12.1.1; extra == 'server'
 Requires-Dist: python-json-logger>=3.1.0; extra == 'server'
 Requires-Dist: sentry-sdk[fastapi]>=2.27.0; extra == 'server'
 Requires-Dist: sqlalchemy-utils>=0.40.0; extra == 'server'

dstack-0.19.36/docker/server/Dockerfile.nebius

@@ -0,0 +1,5 @@
+ARG BASE_IMAGE
+
+FROM ${BASE_IMAGE}
+
+RUN curl -sSL https://storage.eu-north1.nebius.cloud/cli/install.sh | bash

{dstack-0.19.35 → dstack-0.19.36}/docker/server/README.md

@@ -39,7 +39,7 @@ Configuration is updated at ~/.dstack/config.yml
 ## Create SSH fleets
     
 If you want the `dstack` server to run containers on your on-prem servers,
-use [fleets](https://dstack.ai/docs/concepts/fleets#ssh).
+use [fleets](https://dstack.ai/docs/concepts/fleets#ssh-fleets).
 
 ## More information
 

{dstack-0.19.35 → dstack-0.19.36}/docs/assets/stylesheets/landing.css

@@ -242,7 +242,7 @@
     margin-top: 0.6rem;
     margin-bottom: 1.5rem;
     font-size: 19px;
-    font-weight: 300 !important;
+    font-weight: 400 !important;
     text-align: center;
     border-radius: 3px;
     border-color: transparent;
@@ -298,7 +298,7 @@
     background: rgba(0, 0, 0, 0.87);
     border: 1.5px solid rgba(0, 0, 0, 0.87);
     border-radius: 3px;
-    font-weight: 300 !important;
+    font-weight: 400 !important;
     /*margin-right: 10px;*/
 }
 
@@ -353,7 +353,7 @@
 .md-typeset .md-button-secondary:focus {
     background: transparent;
     color: rgba(0, 0, 0, 0.87);
-    border: 0.5px solid rgba(0, 0, 0, 0.87);
+    border: 1px solid rgba(0, 0, 0, 0.87);
     border-radius: 3px;
 }
 

{dstack-0.19.35 → dstack-0.19.36}/docs/blog/posts/amd-mi300x-inference-benchmark.md

@@ -10,7 +10,7 @@ categories:
 
 # Benchmarking Llama 3.1 405B on 8x AMD MI300X GPUs
 
-At `dstack`, we've been adding support for AMD GPUs with [SSH fleets](../../docs/concepts/fleets.md#ssh), 
+At `dstack`, we've been adding support for AMD GPUs with [SSH fleets](../../docs/concepts/fleets.md#ssh-fleets), 
 so we saw this as a great chance to test our integration by benchmarking AMD GPUs. Our friends at 
 [Hot Aisle :material-arrow-top-right-thin:{ .external }](https://hotaisle.xyz/){:target="_blank"}, who build top-tier 
 bare metal compute for AMD GPUs, kindly provided the hardware for the benchmark.
@@ -34,7 +34,7 @@ Here is the spec of the bare metal machine we got:
 ??? info "Set up an SSH fleet"
 
     Hot Aisle provided us with SSH access to the machine. To make it accessible via `dstack`,
-    we created an [SSH fleet](../../docs/concepts/fleets.md#ssh) using the following configuration:
+    we created an [SSH fleet](../../docs/concepts/fleets.md#ssh-fleets) using the following configuration:
 
     <div editor-title="hotaisle.dstack.yml"> 
 
@@ -215,7 +215,7 @@ If you have questions, feedback, or want to help improve the benchmark, please r
 is the primary sponsor of this benchmark, and we are sincerely grateful for their hardware and support.  
 
 If you'd like to use top-tier bare metal compute with AMD GPUs, we recommend going
-with Hot Aisle. Once you gain access to a cluster, it can be easily accessed via `dstack`'s [SSH fleet](../../docs/concepts/fleets.md#ssh) easily.
+with Hot Aisle. Once you gain access to a cluster, it can be easily accessed via `dstack`'s [SSH fleet](../../docs/concepts/fleets.md#ssh-fleets) easily.
 
 ### RunPod
 If you’d like to use on-demand compute with AMD GPUs at affordable prices, you can configure `dstack` to

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/concepts/backends.md

@@ -9,9 +9,8 @@ They can be configured via `~/.dstack/server/config.yml` or through the [project
   * [Container-based](#container-based) – use either `dstack`'s native integration with cloud providers or Kubernetes to orchestrate container-based runs; provisioning in this case is delegated to the cloud provider or Kubernetes.  
   * [On-prem](#on-prem) – use `dstack`'s native support for on-prem servers without needing Kubernetes.  
 
-??? info "dstack Sky"
-    If you're using [dstack Sky :material-arrow-top-right-thin:{ .external }](https://sky.dstack.ai){:target="_blank"},  
-    you can either configure your own backends or use the pre-configured backend that gives you access to compute from the GPU marketplace.
+!!! info "dstack Sky"
+    If you're using [dstack Sky :material-arrow-top-right-thin:{ .external }](https://sky.dstack.ai){:target="_blank"}, backend configuration is optional. dstack Sky lets you use pre-configured backends to access GPU marketplace.
 
 See the examples of backend configuration below.
 

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/concepts/fleets.md

@@ -4,20 +4,19 @@ Fleets act both as pools of instances and as templates for how those instances a
 
 `dstack` supports two kinds of fleets: 
 
-* [Standard fleets](#standard) – dynamically provisioned through configured backends; they are supported with any type of backends: [VM-based](backends.md#vm-based), [container-based](backends.md#container-based), and [Kubernetes](backends.md#kubernetes)
-* [SSH fleets](#ssh) – created using on-prem servers; do not require backends
+* [Backend fleets](#backend-fleets) – dynamically provisioned through configured backends; they are supported with any type of backends: [VM-based](backends.md#vm-based) and [container-based](backends.md#container-based) (incl. [`kubernetes`](backends.md#kubernetes))
+* [SSH fleets](#ssh-fleets) – created using on-prem servers; do not require backends
 
-## Standard fleets { #standard }
+When you run `dstack apply` to start a dev environment, task, or service, `dstack` will reuse idle instances from an existing fleet whenever available.
 
-When you run `dstack apply` to start a dev environment, task, or service, `dstack` will reuse idle instances  
-from an existing fleet whenever available.
+## Backend fleets { #backend-fleets }
 
-If no fleet meets the requirements or has idle capacity, `dstack` can create a new fleet on the fly.  
-However, it’s generally better to define fleets explicitly in configuration files for greater control.  
+If you configured [backends](backends.md), `dstack` can provision fleets on the fly.
+However, it’s recommended to define fleets explicitly.
 
 ### Apply a configuration
 
-Define a fleet configuration as a YAML file in your project directory. The file must have a
+To create a backend fleet, define a configuration as a YAML file in your project directory. The file must have a
 `.dstack.yml` extension (e.g. `.dstack.yml` or `fleet.dstack.yml`).
 
 <div editor-title="examples/misc/fleets/.dstack.yml">
@@ -25,15 +24,21 @@ Define a fleet configuration as a YAML file in your project directory. The file
     ```yaml
     type: fleet
     # The name is optional, if not specified, generated randomly
-    name: my-fleet
+    name: default-fleet
     
     # Can be a range or a fixed number
-    nodes: 2
+    # Allow to provision of up to 2 instances
+    nodes: 0..2
+
     # Uncomment to ensure instances are inter-connected
     #placement: cluster
+
+    # Deprovision instances above the minimum if they remain idle
+    idle_duration: 1h
     
     resources:
-      gpu: 24GB
+      # Allow to provision up to 8 GPUs
+      gpu: 0..8
     ```
     
 </div>
@@ -48,63 +53,49 @@ $ dstack apply -f examples/misc/fleets/.dstack.yml
 Provisioning...
 ---> 100%
 
- FLEET     INSTANCE  BACKEND              GPU             PRICE    STATUS  CREATED 
- my-fleet  0         gcp (europe-west-1)  L4:24GB (spot)  $0.1624  idle    3 mins ago      
-           1         gcp (europe-west-1)  L4:24GB (spot)  $0.1624  idle    3 mins ago    
+ FLEET     INSTANCE  BACKEND  GPU  PRICE  STATUS  CREATED 
+ my-fleet  -         -        -    -      -       -
 ```
 
 </div>
 
-Once the status of instances changes to `idle`, they can be used by dev environments, tasks, and services.
+`dstack` always keeps the minimum number of nodes provisioned. Additional instances, up to the maximum limit, are provisioned on demand.
 
-??? info "Container-based backends"
-    [Container-based](backends.md#container-based) backends don’t support pre-provisioning,
-    so `nodes` can only be set to a range starting with `0`.
-    
-    This means instances are created only when a run starts, and once it finishes, they’re terminated and released back to the provider (either a cloud service or Kubernetes).
+!!! info "Container-based backends"
+    For [container-based](backends.md#container-based) backends  (such as `kubernetes`, `runpod`, etc), `nodes` must be defined as a range starting with `0`. In these cases, instances are provisioned on demand as needed.
 
-    <div editor-title=".dstack.yml">
+    <!-- TODO: Ensure the user sees the error or warning otherwise -->
 
-    ```yaml
-    type: fleet
-    # The name is optional, if not specified, generated randomly
-    name: my-fleet
-    
-    # Specify the number of instances
-    nodes: 0..2
-    # Uncomment to ensure instances are inter-connected
-    #placement: cluster
-    
-    resources:
-      gpu: 24GB
-    ```
+??? info "Target number of nodes"
 
-    </div>
+    If `nodes` is defined as a range, you can start with more than the minimum number of instances by using the `target` parameter when creating the fleet.
 
-### Configuration options
+    <div editor-title=".dstack.yml"> 
 
-#### Nodes { #nodes }
+    ```yaml
+    type: fleet
 
-The `nodes` property controls how many instances to provision and maintain in the fleet:
+    name: my-fleet
 
-<div editor-title=".dstack.yml"> 
+    nodes:
+      min: 0
+      max: 2
 
-```yaml
-type: fleet
+      # Provision 2 instances initially
+      target: 2
 
-name: my-fleet
+    # Deprovision instances above the minimum if they remain idle
+    idle_duration: 1h
+    ```
 
-nodes:
-  min: 1 # Always maintain at least 1 idle instance. Can be 0.
-  target: 2 # (Optional) Provision 2 instances initially
-  max: 3 # (Optional) Do not allow more than 3 instances
-```
+    </div>
 
-</div>
+By default, when you submit a [dev environment](dev-environments.md), [task](tasks.md), or [service](services.md), `dstack` tries all available fleets. However, you can explicitly specify the [`fleets`](../reference/dstack.yml/dev-environment.md#fleets) in your run configuration
+or via [`--fleet`](../reference/cli/dstack/apply.md#fleet) with `dstack apply`.
 
-`dstack` ensures the fleet always has at least `nodes.min` instances, creating new instances in the background if necessary. If you don't need to keep instances in the fleet forever, you can set `nodes.min` to `0`. By default, `dstack apply` also provisions `nodes.min` instances. The `nodes.target` property allows provisioning more instances initially than needs to be maintained.
+### Configuration options
 
-#### Placement { #standard-placement }
+#### Placement { #backend-placement }
 
 To ensure instances are interconnected (e.g., for
 [distributed tasks](tasks.md#distributed-tasks)), set `placement` to `cluster`. 
@@ -190,9 +181,9 @@ and their quantity. Examples: `nvidia` (one NVIDIA GPU), `A100` (one A100), `A10
 > If you’re unsure which offers (hardware configurations) are available from the configured backends, use the
 > [`dstack offer`](../reference/cli/dstack/offer.md#list-gpu-offers) command to list them.
 
-#### Blocks { #standard-blocks }
+#### Blocks { #backend-blocks }
 
-For standard fleets, `blocks` function the same way as in SSH fleets. 
+For backend fleets, `blocks` function the same way as in SSH fleets. 
 See the [`Blocks`](#ssh-blocks) section under SSH fleets for details on the blocks concept.
 
 <div editor-title=".dstack.yml">
@@ -214,10 +205,10 @@ blocks: 4
 #### Idle duration
 
 By default, fleet instances stay `idle` for 3 days and can be reused within that time.
-If the fleet is not reused within this period, it is automatically terminated.
+If an instance is not reused within this period, it is automatically terminated.
 
 To change the default idle duration, set
-[`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the run configuration (e.g., `0s`, `1m`, or `off` for
+[`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the fleet configuration (e.g., `0s`, `1m`, or `off` for
 unlimited).
 
 <div editor-title="examples/misc/fleets/.dstack.yml">
@@ -272,13 +263,13 @@ retry:
 </div>
 
 !!! info "Reference"
-    Standard fleets support many more configuration options,
+    Backend fleets support many more configuration options,
     incl. [`backends`](../reference/dstack.yml/fleet.md#backends), 
     [`regions`](../reference/dstack.yml/fleet.md#regions), 
     [`max_price`](../reference/dstack.yml/fleet.md#max_price), and
     among [others](../reference/dstack.yml/fleet.md).
 
-## SSH fleets { #ssh }
+## SSH fleets { #ssh-fleets }
 
 If you have a group of on-prem servers accessible via SSH, you can create an SSH fleet.
 
@@ -392,7 +383,7 @@ By default, a job uses the entire instance—e.g., all 8 GPUs. To allow multiple
           # As many as possible, according to numbers of GPUs and CPUs
           blocks: auto
         - hostname: 3.255.177.53
-          # Do not sclice. This is the default value, may be omitted
+          # Do not slice. This is the default value, may be omitted
           blocks: 1
     ```
 

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/concepts/snippets/manage-fleets.ext

@@ -1,10 +1,10 @@
 ### Creation policy
 
 By default, when you run `dstack apply` with a dev environment, task, or service,
-if no `idle` instances from the available fleets meet the requirements, `dstack` creates a new fleet 
+if no `idle` instances from the available fleets meet the requirements, `dstack` provisions a new instance
 using configured backends.
 
-To ensure `dstack apply` doesn't create a new fleet but reuses an existing one,
+To ensure `dstack apply` doesn't provision a new instance but reuses an existing one,
 pass `-R` (or `--reuse`) to `dstack apply`.
 
 <div class="termy">
@@ -19,12 +19,7 @@ Or, set [`creation_policy`](../reference/dstack.yml/dev-environment.md#creation_
 
 ### Idle duration
 
-If a fleet is created automatically, it stays `idle` for 5 minutes by default and can be reused within that time.
-If the fleet is not reused within this period, it is automatically terminated.
+If a run provisions a new instance, the instance stays `idle` for 5 minutes by default and can be reused within that time.
+If the instance is not reused within this period, it is automatically terminated.
 To change the default idle duration, set
-[`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the run configuration (e.g., `0s`, `1m`, or `off` for
-unlimited).
-
-!!! info "Fleets"
-    For greater control over fleet provisioning, it is recommended to create
-    [fleets](fleets.md) explicitly.
+[`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the run configuration (e.g., `0s`, `1m`, or `off` for unlimited).

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/concepts/tasks.md

@@ -170,12 +170,8 @@ Use `DSTACK_MASTER_NODE_IP`, `DSTACK_NODES_IPS`, `DSTACK_NODE_RANK`, and other
     For convenience, `~/.ssh/config` is preconfigured with these options, so a simple `ssh <node_ip>` is enough.
     For a list of nodes IPs check the `DSTACK_NODES_IPS` environment variable.
 
-!!! info "Fleets"
-    Distributed tasks can only run on fleets with
-    [cluster placement](fleets.md#cloud-placement).
-    While `dstack` can provision such fleets automatically, it is
-    recommended to create them via a fleet configuration
-    to ensure the highest level of inter-node connectivity.
+!!! info "Cluster fleets"
+    To run distributed tasks, you need to create a fleet with [`placement: cluster`](fleets.md#cloud-placement).
 
 > See the [Clusters](../guides/clusters.md) guide for more details on how to use `dstack` on clusters.
 

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/guides/protips.md

@@ -190,11 +190,9 @@ See more Docker examples [here](https://github.com/dstackai/dstack/tree/master/e
 ### Creation policy
 
 By default, when you run `dstack apply` with a dev environment, task, or service,
-`dstack` reuses `idle` instances from an existing [fleet](../concepts/fleets.md).
-If no `idle` instances match the requirements, `dstack` automatically creates a new fleet 
-using configured backends.
+if no `idle` instances from the available fleets meet the requirements, `dstack` provisions a new instance using configured backends.
 
-To ensure `dstack apply` doesn't create a new fleet but reuses an existing one,
+To ensure `dstack apply` doesn't provision a new instance but reuses an existing one,
 pass `-R` (or `--reuse`) to `dstack apply`.
 
 <div class="termy">
@@ -205,16 +203,14 @@ $ dstack apply -R -f examples/.dstack.yml
 
 </div>
 
+Or, set [`creation_policy`](../reference/dstack.yml/dev-environment.md#creation_policy) to `reuse` in the run configuration.
+
 ### Idle duration
 
-If a fleet is created automatically, it stays `idle` for 5 minutes by default and can be reused within that time.
-If the fleet is not reused within this period, it is automatically terminated.
+If a run provisions a new instance, the instance stays `idle` for 5 minutes by default and can be reused within that time.
+If the instance is not reused within this period, it is automatically terminated.
 To change the default idle duration, set
-[`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the run configuration (e.g., `0s`, `1m`, or `off` for
-unlimited).
-
-> For greater control over fleet provisioning, configuration, and lifecycle management, it is recommended to use
-> [fleets](../concepts/fleets.md) directly.
+[`idle_duration`](../reference/dstack.yml/fleet.md#idle_duration) in the run configuration (e.g., `0s`, `1m`, or `off` for unlimited).
 
 ## Volumes
 

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/installation/index.md

@@ -1,8 +1,8 @@
 # Installation
 
-!!! info "dstack Sky"
+<!-- !!! info "dstack Sky"
     If you don't want to host the `dstack` server (or want to access GPU marketplace),
-    skip installation and proceed to [dstack Sky :material-arrow-top-right-thin:{ .external }](https://sky.dstack.ai){:target="_blank"}.
+    skip installation and proceed to [dstack Sky :material-arrow-top-right-thin:{ .external }](https://sky.dstack.ai){:target="_blank"}. -->
 
 ## Set up the server
 

{dstack-0.19.35 → dstack-0.19.36}/docs/docs/quickstart.md

@@ -1,6 +1,6 @@
 # Quickstart
 
-> Before using `dstack`, ensure you've [installed](installation/index.md) the server, or signed up for [dstack Sky :material-arrow-top-right-thin:{ .external }](https://sky.dstack.ai){:target="_blank"}.
+> Before using `dstack`, ensure you've [installed](installation/index.md) the server.
 
 ## Set up a directory
     
@@ -14,13 +14,64 @@ $ mkdir quickstart && cd quickstart
 
 </div>
 
+## Create a fleet
+
+If [backends](concepts/backends.md) are configured, `dstack` can create a new [backend fleet](concepts/fleets.md#backend-fleets) on the fly. However, it’s recommended to create them explicitly.
+
+<h3>Define a configuration</h3>
+
+Create the following fleet configuration inside your project folder:
+
+<div editor-title="fleet.dstack.yml"> 
+
+```yaml
+type: fleet
+name: default
+
+# Allow to provision of up to 2 instances
+nodes: 0..2
+
+# Deprovision instances above the minimum if they remain idle
+idle_duration: 1h
+
+resources:
+  # Allow to provision up to 8 GPUs
+  gpu: 0..8
+```
+
+</div>
+
+<h3>Apply the configuration</h3>
+
+Apply the configuration via [`dstack apply`](reference/cli/dstack/apply.md):
+
+<div class="termy">
+
+```shell
+$ dstack apply -f fleet.dstack.yml
+    
+     #  BACKEND  REGION           RESOURCES                 SPOT  PRICE
+     1  gcp      us-west4         2xCPU, 8GB, 100GB (disk)  yes   $0.010052
+     2  azure    westeurope       2xCPU, 8GB, 100GB (disk)  yes   $0.0132
+     3  gcp      europe-central2  2xCPU, 8GB, 100GB (disk)  yes   $0.013248
+
+Fleet cloud-fleet does not exist yet.
+Create the fleet? [y/n]: y
+ FLEET          INSTANCE  BACKEND  RESOURCES  PRICE  STATUS  CREATED 
+ defalut-fleet  -         -        -          -      -       10:36
+```
+
+</div>
+
+Alternatively, you can create an [SSH fleet](concepts/fleets#ssh-fleets).
+
 ## Submit your first run
 
 `dstack` supports three types of run configurations.
 
 === "Dev environment"
 
-    A dev environment lets you provision an instance and access it with your desktop IDE.
+    A [dev environment](concepts/dev-environments.md) lets you provision an instance and access it with your desktop IDE.
 
     <h3>Define a configuration</h3>
 
@@ -76,7 +127,7 @@ $ mkdir quickstart && cd quickstart
 
 === "Task"
 
-    A task allows you to schedule a job or run a web app. Tasks can be distributed and can forward ports.
+    A [task](concepts/tasks.md) allows you to schedule a job or run a web app. Tasks can be distributed and can forward ports.
 
     <h3>Define a configuration</h3>
 
@@ -140,7 +191,7 @@ $ mkdir quickstart && cd quickstart
 
 === "Service"
 
-    A service allows you to deploy a model or any web app as an endpoint.
+    A [service](concepts/services.md) allows you to deploy a model or any web app as an endpoint.
 
     <h3>Define a configuration</h3>
 

{dstack-0.19.35 → dstack-0.19.36}/docs/overrides/home.html

@@ -68,15 +68,21 @@
                         <!-- <span class="icon"><svg viewBox="0 0 13 10" xmlns="http://www.w3.org/2000/svg"><path d="M12.823 4.164L8.954.182a.592.592 0 0 0-.854 0 .635.635 0 0 0 0 .88l2.836 2.92H.604A.614.614 0 0 0 0 4.604c0 .344.27.622.604.622h10.332L8.1 8.146a.635.635 0 0 0 0 .88.594.594 0 0 0 .854 0l3.869-3.982a.635.635 0 0 0 0-.88z" fill-rule="nonzero" fill="currentColor" class="fill-main"></path></svg></span> -->
                     </a>
 
-                    <a href="https://sky.dstack.ai" target="_blank" 
+                    <a href="/docs/" target="_blank" 
+                       class="md-button md-button-secondary"
+                        style="min-width: 225px;">
+                        <span>Documentation</span>
+                    </a>
+
+                    <!-- <a href="https://sky.dstack.ai" target="_blank" 
                        class="md-button md-button--primary sky external"
                         style="min-width: 225px;">
                         <span>Sign up free</span>
-                    </a>
+                    </a> -->
                 </div>
             </div>
             <div class="tx-landing__hero_button_container_text" style="text-align: center; font-size: 85%; margin-top: 1.25rem">
-                Open-source self-hosted or fully-managed. Setup takes a few minutes.
+                One control plane for GPUs across cloud, Kubernetes, and on-prem.
             </div>
         </div>
 

dstack-0.19.36/examples/clusters/efa/fleet.dstack.yml

@@ -0,0 +1,8 @@
+type: fleet
+name: my-efa-fleet
+
+nodes: 2
+placement: cluster
+
+resources:
+  gpu: H100:8

{dstack-0.19.35 → dstack-0.19.36}/examples/clusters/nccl-tests/README.md

@@ -1,6 +1,9 @@
 # NCCL tests
 
-This example shows how to run distributed [NCCL tests :material-arrow-top-right-thin:{ .external }](https://github.com/NVIDIA/nccl-tests){:target="_blank"} with MPI using `dstack`.
+This example shows how to run [NCCL tests :material-arrow-top-right-thin:{ .external }](https://github.com/NVIDIA/nccl-tests){:target="_blank"} on a cluster using [distributed tasks](https://dstack.ai/docs/concepts/tasks#distributed-tasks).
+
+!!! info "Prerequisites"
+    Before running a distributed task, make sure to create a fleet with `placement` set to `cluster` (can be a [managed fleet](https://dstack.ai/docs/concepts/fleets#backend-placement) or an [SSH fleet](https://dstack.ai/docs/concepts/fleets#ssh-placement)).
 
 ## Running as a task
 
@@ -76,5 +79,5 @@ The source-code of this example can be found in
 
 ## What's next?
 
-1. Check [dev environments](https://dstack.ai/docs/dev-environments), [tasks](https://dstack.ai/docs/tasks), 
-   [services](https://dstack.ai/docs/services), and [fleets](https://dstack.ai/docs/concepts/fleets).
+1. Check [dev environments](https://dstack.ai/docs/concepts/dev-environments), [tasks](https://dstack.ai/docs/concepts/tasks), 
+   [services](https://dstack.ai/docsconcepts/services), and [fleets](https://dstack.ai/docs/concepts/fleets).