Skip to content

Commit f31898c

Browse files
docs: Update load balancing payload limit documentation to 30 MB (#443)
Co-authored-by: promptless[bot] <179508745+promptless[bot]@users.noreply.github.com> Co-authored-by: Mo King <muhsinking@gmail.com>
1 parent 4c509cd commit f31898c

File tree

1 file changed

+10
-0
lines changed

1 file changed

+10
-0
lines changed

serverless/load-balancing/overview.mdx

Lines changed: 10 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -181,6 +181,16 @@ If your server is misconfigured and the ports are not correctly opened, your wor
181181

182182
</Warning>
183183

184+
## Payload limits
185+
186+
Load balancing endpoints have a 30 MB payload limit for both requests and responses.
187+
188+
If you need to handle payloads larger than 30 MB, you can try these approaches:
189+
190+
- Use a [network volume](storage/network-volumes) to store model artifacts and large datasets for access during runtime.
191+
- Implement chunking strategies to split large payloads into smaller pieces.
192+
193+
184194
## Handling cold start errors
185195

186196
When you first send a request to a load balancing endpoint, you might get a "no workers available" error. This happens because workers need time to initialize, i.e. the server is up, but the health check at `/ping` isn't passing yet.

0 commit comments

Comments
 (0)