[GH-ISSUE #6217] batch embed 500 error: no slots available after 10 retries #29646

Closed
opened 2026-04-22 08:42:04 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Schumpeterx on GitHub (Aug 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6217

What is the issue?

I try to use 10 threads to send batch embedding request to /api/embed, and sometime got the below error:

Aug 07 09:19:18 *-gpu ollama[345349]: time=2024-08-07T09:19:18.764+08:00 level=ERROR source=routes.go:368 msg="embedding generation failed" error="no slots available after 10 retries"

Is it a bug or not? if not, how to increase the number of available slots?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.3.0

Originally created by @Schumpeterx on GitHub (Aug 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6217 ### What is the issue? I try to use 10 threads to send batch embedding request to `/api/embed`, and sometime got the below error: ``` Aug 07 09:19:18 *-gpu ollama[345349]: time=2024-08-07T09:19:18.764+08:00 level=ERROR source=routes.go:368 msg="embedding generation failed" error="no slots available after 10 retries" ``` Is it a bug or not? if not, how to increase the number of available slots? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.3.0
GiteaMirror added the bug label 2026-04-22 08:42:04 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#29646