github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4310] updating to v0.1.34 from v0.1.33 with models from file from llama3:70b-instruct-q4_0 with 23k SYSTEM data yields in >100s processing and 504 response #2687

New Issue
Closed
opened 2026-04-12 13:00:50 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 13:00:50 -05:00
Owner
Copy Link

Originally created by @aiboogie on GitHub (May 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4310

What is the issue?

I was using ollama v0.1.33 with models from file from llama3:70b-instruct-q4_0 with 23k SYSTEM data
Each prompt was not taking more than 20s (except the initial model load request) on a M1 Ultra 128GB Ram and 48 GPU cores.
I updated today to v0.1.34, using the same generated model, for all requests i get a huge processing time when reaching 100s it disconnects execution with a 504 response code.

Downgrading back to v0.1.33 solves the problem, so it must be something with v0.1.34

Please advise,
Thanks!

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.34

Originally created by @aiboogie on GitHub (May 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4310 ### What is the issue? I was using ollama v0.1.33 with models from file from llama3:70b-instruct-q4_0 with 23k SYSTEM data Each prompt was not taking more than 20s (except the initial model load request) on a M1 Ultra 128GB Ram and 48 GPU cores. I updated today to v0.1.34, using the same generated model, for all requests i get a huge processing time when reaching 100s it disconnects execution with a 504 response code. Downgrading back to v0.1.33 solves the problem, so it must be something with v0.1.34 Please advise, Thanks! ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.34
GiteaMirror added the bug label 2026-04-12 13:00:50 -05:00
GiteaMirror commented 2026-04-12 13:00:51 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (May 11, 2024):

Hi @aiboogie would it be possible to try again with 0.1.35? It's possible an inference subprocess from Ollama was hanging around – upgrading to 0.1.35 and restarting should clear any of those. Let me know if you're still seeing this afterwards 😊

<!-- gh-comment-id:2105460379 --> @jmorganca commented on GitHub (May 11, 2024): Hi @aiboogie would it be possible to try again with 0.1.35? It's possible an inference subprocess from Ollama was hanging around – upgrading to 0.1.35 and restarting should clear any of those. Let me know if you're still seeing this afterwards 😊
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
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#2687
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?