Home
Model APIs
Serverless
Compute- Added
fal runners stopcommand documentation - Clarified app behavior in case of crash/timeout scenarios
- Fixed redirect issues for model APIs and serverless features
- Added documentation for
fal files mvandfal files rmcommands
- Added new error handling documentation route
- Updated quick start guide with new Hello World app example
- Added new deployment page
- Added comprehensive App Files documentation
- Updated favicon from PNG to SVG format
- Streamlined client library documentation
- Reviewed and cleaned up style of all documentation examples
- Updated deployment command examples for clarity
- Added
fal runners logscommand documentation
- Added MCP pages under model-apis, serverless, and compute sections
- Added webhook documentation page
- Added new Distributed Computing section
- Added multi-GPU inference tutorial with architecture overview
- Updated GitHub links to point to fal-ai-community repository
- fal Docs 2.0 released.
- Fixed redirects for private serverless models
- Added
fal.api.SyncServerlessClientfor synchronous operations - Adjusted client naming conventions
- Enhanced model deployment tutorials with example projects
- Added comprehensive queue documentation
- Improved app liveness/readiness probe documentation
- Documented setup success indicators and 503/504 error handling
- Documented
concurrency_buffer_percconfiguration option
- Added section about secrets in requirements
- Explained execution order for serverless functions
- Updated workflow JSON schema
- Added comprehensive
fal.AppAPI reference - Improved scaling documentation
- Added cancellation handling documentation
- Added
x-fal-request-idheader to examples - Added 1/1 min/buffer scaling example
- Clarified WebSocket import from FastAPI
- Added
x-fal-store-iosection in payloads documentation
- Updated Google Artifact Registry docs to use service account keys
- Improved
/datavolume documentation
- Added endpoint for scaling applications
- Updated scaling settings documentation for redeployment behavior
- Moved model loading tips to dedicated page
- Added tips on improving
/datavolume performance
- Updated custom workflow example
- Fixed broken links across the site
- Updated compliance types documentation
- Added custom workflow UI documentation
- Updated core concepts machine types
- Comprehensive update to getting started guide
- Added
fal runto quick start - Added payloads documentation section
- Added n8n integration guide
- Added comprehensive compute documentation
- Improved buffer and scaling documentation with examples
- Fixed
concurrency_buffertypos - Clarified
concurrency_bufferprecedence overmin_concurrency - Added Vercel redirects to avoid internal 404s
- Updated default machine type
- Updated machine resources documentation
- Updated documentation for scale settings
- Migrated deployment to GitHub Actions