github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 20:54:54 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7545] ERROR source=runner.go:426 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" #82480

New Issue
Closed
opened 2026-05-09 14:18:15 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-09 14:18:15 -05:00
Owner
Copy Link

Originally created by @wuhongsheng on GitHub (Nov 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7545

What is the issue?

ERROR source=runner.go:426 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.4

Originally created by @wuhongsheng on GitHub (Nov 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7545 ### What is the issue? ERROR source=runner.go:426 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.4
GiteaMirror added the bugneeds more info labels 2026-05-09 14:18:15 -05:00
GiteaMirror commented 2026-05-09 14:18:17 -05:00
Author
Owner
Copy Link

@wuhongsheng commented on GitHub (Nov 7, 2024):

cheap_model_max_async=2,
best_model_max_async=2,

<!-- gh-comment-id:2461605202 --> @wuhongsheng commented on GitHub (Nov 7, 2024): cheap_model_max_async=2, best_model_max_async=2,
GiteaMirror commented 2026-05-09 14:18:17 -05:00
Author
Owner
Copy Link

@pengfan7758258 commented on GitHub (Nov 7, 2024):

The version is too new. I downgraded to version 0.3.14, and the issue was resolved. However, I noticed that in version 0.4, the GPU utilization decreased. Looking forward to a more stable release in future versions.

<!-- gh-comment-id:2461913295 --> @pengfan7758258 commented on GitHub (Nov 7, 2024): The version is too new. I downgraded to version 0.3.14, and the issue was resolved. However, I noticed that in version 0.4, the GPU utilization decreased. Looking forward to a more stable release in future versions.
GiteaMirror commented 2026-05-09 14:18:18 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 7, 2024):

@wuhongsheng Can you please post the full server logs?

<!-- gh-comment-id:2462855934 --> @jessegross commented on GitHub (Nov 7, 2024): @wuhongsheng Can you please post the full [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues)?
GiteaMirror commented 2026-05-09 14:18:18 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 14, 2024):

This may be fixed in main - if anyone who is experiencing this issue can build from source and test it, that would be helpful to confirm.

<!-- gh-comment-id:2475170375 --> @jessegross commented on GitHub (Nov 14, 2024): This may be fixed in `main` - if anyone who is experiencing this issue can build from source and test it, that would be helpful to confirm.
GiteaMirror commented 2026-05-09 14:18:20 -05:00
Author
Owner
Copy Link

@fce2 commented on GitHub (Nov 17, 2024):

just fyi, with ollama 0.4.2 i also get this error (using llama2-11b)

here is some log, loosk like the "limit" is not set correct (set to 2k, but llama2 has 128k)

time=2024-11-17T09:22:10.460+01:00 level=WARN source=runner.go:122 msg="input exceeds context length" prompt=54273 limit=2048
time=2024-11-17T09:22:10.635+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-17T09:22:10.809+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-17T09:22:10.810+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-17T09:22:10.949+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-17T09:22:11.167+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-17T09:22:11.370+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
time=2024-11-17T09:22:11.590+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1"
<!-- gh-comment-id:2481028111 --> @fce2 commented on GitHub (Nov 17, 2024): just fyi, with ollama 0.4.2 i also get this error (using llama2-11b) here is some log, loosk like the "limit" is not set correct (set to 2k, but llama2 has 128k) ``` time=2024-11-17T09:22:10.460+01:00 level=WARN source=runner.go:122 msg="input exceeds context length" prompt=54273 limit=2048 time=2024-11-17T09:22:10.635+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-17T09:22:10.809+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-17T09:22:10.810+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-17T09:22:10.949+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-17T09:22:11.167+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-17T09:22:11.370+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" time=2024-11-17T09:22:11.590+01:00 level=ERROR source=runner.go:429 msg="failed to decode batch" error="could not find a KV slot for the batch - try reducing the size of the batch or increase the context. code: 1" ```
GiteaMirror commented 2026-05-09 14:18:23 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 21, 2024):

@fce2 (or others that are experiencing this issue), can you give it a try with 0.4.3-rc0 (or later)? I believe that this error should be fixed now.

<!-- gh-comment-id:2492003779 --> @jessegross commented on GitHub (Nov 21, 2024): @fce2 (or others that are experiencing this issue), can you give it a try with 0.4.3-rc0 (or later)? I believe that this error should be fixed now.
GiteaMirror commented 2026-05-09 14:18:25 -05:00
Author
Owner
Copy Link

@fce2 commented on GitHub (Nov 22, 2024):

Hi Jesse,
just tested with 0.4.3, looks good now !
!! THANKS !!

<!-- gh-comment-id:2493307647 --> @fce2 commented on GitHub (Nov 22, 2024): Hi Jesse, just tested with 0.4.3, looks good now ! !! THANKS !!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug needs more info
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#82480
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?