github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5602] Running latest version 0.2.1 running slowly and not returning output for long text input #29262

New Issue
Closed
opened 2026-04-22 07:58:44 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 07:58:44 -05:00
Owner
Copy Link

Originally created by @jillvillany on GitHub (Jul 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5602

Originally assigned to: @jmorganca on GitHub.

What is the issue?

I am running ollama on an AWS ml.p3.2xlarge SageMaker notebook instance.

When I install the latest version, 0.2.1, the response time on a langchain chain running an extract names prompt on a page of text using llama3:latest is about 8 seconds and doesn't return any names.

However, when I install version 0.1.37, the response time goes down to under a second and I get an accurate response with people's names found in the text.

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

0.2.1

Originally created by @jillvillany on GitHub (Jul 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5602 Originally assigned to: @jmorganca on GitHub. ### What is the issue? I am running ollama on an AWS ml.p3.2xlarge SageMaker notebook instance. When I install the latest version, 0.2.1, the response time on a langchain chain running an extract names prompt on a page of text using llama3:latest is about 8 seconds and doesn't return any names. However, when I install version 0.1.37, the response time goes down to under a second and I get an accurate response with people's names found in the text. ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.2.1
GiteaMirror added the performancebug labels 2026-04-22 07:58:44 -05:00
GiteaMirror commented 2026-04-22 07:58:46 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 10, 2024):

Hi there sorry you’re hitting this. I’m working on a fix, just to confirm - this instance type has V100 GPUs right?

<!-- gh-comment-id:2220684700 --> @jmorganca commented on GitHub (Jul 10, 2024): Hi there sorry you’re hitting this. I’m working on a fix, just to confirm - this instance type has V100 GPUs right?
GiteaMirror commented 2026-04-22 07:58:47 -05:00
Author
Owner
Copy Link

@Demirrr commented on GitHub (Jul 11, 2024):

I have a similar issue with NVIDIA H100 GPUs

Update: I do not observe the slow inference problem with v0.2.8. Thank you for the release

<!-- gh-comment-id:2222833996 --> @Demirrr commented on GitHub (Jul 11, 2024): I have a similar issue with NVIDIA H100 GPUs Update: I do not observe the slow inference problem with v0.2.8. Thank you for the release
GiteaMirror commented 2026-04-22 07:58:47 -05:00
Author
Owner
Copy Link

@rhelenagh commented on GitHub (Jul 14, 2024):

I have the same situation, with a Windows 11 operating system.

<!-- gh-comment-id:2227395080 --> @rhelenagh commented on GitHub (Jul 14, 2024): I have the same situation, with a Windows 11 operating system.
GiteaMirror commented 2026-04-22 07:58:47 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jun 19, 2025):

This should be fixed now – there was an issue last year with V100 GPUs that should be resolved. If not feel free to let me know and I can reopen!

<!-- gh-comment-id:2988694111 --> @jmorganca commented on GitHub (Jun 19, 2025): This should be fixed now – there was an issue last year with V100 GPUs that should be resolved. If not feel free to let me know and I can reopen!
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 performance
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#29262
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?