Skip to content

docs: Update Flash deployment size limit from 500MB to 1.5GB #578

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
muhsinking merged 3 commits into from
Mar 23, 2026
Merged

docs: Update Flash deployment size limit from 500MB to 1.5GB #578

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
68bfdb3
Update Flash deployment size limit from 500MB to 1.5GB
promptless[bot] Mar 23, 2026
2a67cdf
Merge branch 'main' into promptless/flash-tarball-size-limit-increase
muhsinking Mar 23, 2026
fa1968f
Merge branch 'main' into promptless/flash-tarball-size-limit-increase
muhsinking Mar 23, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion flash/apps/apps-and-environments.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@ When you run `flash deploy`, Flash creates and uploads a build artifact, then pr
4. **Activate environment**: The environment is linked to the build and endpoints.

<Tip>
You're **not** building custom Docker images. Flash uses pre-built images that extract your tarball and run your code. This is why deployments are fast (no image build step) and limited to 500 MB (code and dependencies only).
You're **not** building custom Docker images. Flash uses pre-built images that extract your tarball and run your code. This is why deployments are fast (no image build step) and limited to 1.5 GB (code and dependencies only).
</Tip>

## Common environment patterns
Expand Down
6 changes: 3 additions & 3 deletions flash/apps/deploy-apps.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,7 +184,7 @@ Press `Ctrl+C` to stop the preview environment.

## Managing deployment size

Runpod Serverless has a **500MB deployment limit**. Flash automatically excludes packages that are pre-installed in the base image:
Runpod Serverless has a **1.5GB deployment limit**. Flash automatically excludes packages that are pre-installed in the base image:
Copy link
Copy Markdown
Contributor Author

@promptless promptless Bot Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Citation: Deployment limit update from PR #258. The internal Flash docs (flash-build.md, flash-deploy.md) were also updated to 1.5GB in the same PR.
View source


- `torch`, `torchvision`, `torchaudio`
- `numpy`, `triton`
Expand Down Expand Up @@ -236,7 +236,7 @@ When you deploy a Flash app, you're deploying a **build artifact** (tarball) ont

### The build artifact

The `.flash/artifact.tar.gz` file (max 500 MB) contains:
The `.flash/artifact.tar.gz` file (max 1.5 GB) contains:

<Tree>
<Tree.Folder name="artifact.tar.gz" defaultOpen>
Expand Down Expand Up @@ -328,7 +328,7 @@ If the build process can't find your endpoint functions:

### Deployment size limit exceeded

Base image packages are auto-excluded. If your deployment still exceeds 500MB, use `--exclude` to skip additional packages:
Base image packages are auto-excluded. If your deployment still exceeds 1.5GB, use `--exclude` to skip additional packages:

```bash
flash deploy --exclude scipy,pandas
Expand Down
2 changes: 1 addition & 1 deletion flash/apps/overview.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ Building a Flash application follows a clear progression from initialization to

When you deploy an app, Runpod:

1. Packages your code, dependencies, and deployment manifest into a tarball (max 500 MB).
1. Packages your code, dependencies, and deployment manifest into a tarball (max 1.5 GB).
2. Uploads the tarball to Runpod.
3. Provisions independent Serverless endpoints based on your [endpoint configurations](/flash/create-endpoints).

Expand Down
2 changes: 1 addition & 1 deletion flash/cli/build.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,7 +81,7 @@ Image tags follow the pattern `py{version}-{tag}` (for example, `runpod/flash:py

## Managing deployment size

Runpod Serverless has a **500MB deployment limit**. Flash automatically excludes packages that are pre-installed in the base image:
Runpod Serverless has a **1.5GB deployment limit**. Flash automatically excludes packages that are pre-installed in the base image:
Copy link
Copy Markdown
Contributor Author

@promptless promptless Bot Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Citation: Updated size limit based on change in constants.py where MAX_TARBALL_SIZE_MB was increased from 500 to 1500. The PR description notes this supports ML workloads with larger dependencies.
View source


- `torch`, `torchvision`, `torchaudio`
- `numpy`, `triton`
Expand Down
4 changes: 2 additions & 2 deletions flash/cli/deploy.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,7 +50,7 @@ Skip transitive dependencies during pip install. Useful when the base image alre
</ResponseField>

<ResponseField name="--exclude" type="string">
Comma-separated packages to exclude (e.g., `torch,torchvision`). Use this to stay under the 500MB deployment limit.
Comma-separated packages to exclude (e.g., `torch,torchvision`). Use this to stay under the 1.5GB deployment limit.
</ResponseField>

<ResponseField name="--output, -o" type="string" default="artifact.tar.gz">
Expand Down Expand Up @@ -204,7 +204,7 @@ This builds your project and runs it in Docker containers locally:

## Managing deployment size

Runpod Serverless has a **500MB limit**. Flash automatically excludes packages that are pre-installed in the base image (`torch`, `torchvision`, `torchaudio`, `numpy`, `triton`).
Runpod Serverless has a **1.5GB limit**. Flash automatically excludes packages that are pre-installed in the base image (`torch`, `torchvision`, `torchaudio`, `numpy`, `triton`).
Copy link
Copy Markdown
Contributor Author

@promptless promptless Bot Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Citation: Size limit increase reflects the MAX_TARBALL_SIZE_MB = 1500 constant change in the Flash codebase.
View source


If the deployment is still too large, use `--exclude` to skip additional packages:

Expand Down
4 changes: 2 additions & 2 deletions flash/troubleshooting.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,10 +183,10 @@ Duplicate route 'POST /process' in endpoint 'my-api'

**Error:**
```
Tarball exceeds maximum size. File size: 512.5MB, Max: 500MB
Tarball exceeds maximum size. File size: 1.6GB, Max: 1.5GB
Copy link
Copy Markdown
Contributor Author

@promptless promptless Bot Mar 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Citation: Updated error message example to reflect new 1.5GB max. The PR updated tests from 600MB to 1600MB to exceed the new limit.
View source

```

**Cause:** The deployment package exceeds the 500MB limit.
**Cause:** The deployment package exceeds the 1.5GB limit.

**Solution:**

Expand Down
Loading