github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12916] The auto-start Ollama service cannot output in parallel. #34323

New Issue
Open
opened 2026-04-22 17:46:29 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-22 17:46:29 -05:00
Owner
Copy Link

Originally created by @XiaZixun on GitHub (Nov 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12916

What is the issue?

I use brew services to start ollama at boot and inject the environment variable OLLAMA_NUM_PARALLEL = 4 via a plist.
However, the automatically started ollama cannot achieve parallel output, even though checking the environment variable shows the correct value.

❯ launchctl print gui/$UID/homebrew.mxcl.ollama | grep OLLAMA_NUM_PARALLEL
                OLLAMA_NUM_PARALLEL => 4

At this point, I only need to run brew services restart ollama without setting any additional environment variables, and ollama will correctly perform parallel output.

I'm not entirely sure if I have set it up correctly. What should the correct method for persistently setting ollama's environment variables be?

My ~/Library/LaunchAgents/environments.plist is as follows:

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
  <dict>
    <key>Label</key>
    <string>environment.variables.user</string>

    <key>ProgramArguments</key>
    <array>
      <string>/bin/sh</string>
      <string>-c</string>
      <string>
        /bin/launchctl setenv OLLAMA_NUM_PARALLEL 4;
        /bin/launchctl setenv OLLAMA_MAX_LOADED_MODELS 4;
      </string>
    </array>

    <key>RunAtLoad</key>
    <true/>
  </dict>
</plist>

Relevant log output

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.12.9

Originally created by @XiaZixun on GitHub (Nov 3, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12916 ### What is the issue? I use `brew services` to start ollama at boot and inject the environment variable `OLLAMA_NUM_PARALLEL = 4` via a plist. However, the automatically started ollama cannot achieve parallel output, even though checking the environment variable shows the correct value. ``` ❯ launchctl print gui/$UID/homebrew.mxcl.ollama | grep OLLAMA_NUM_PARALLEL OLLAMA_NUM_PARALLEL => 4 ``` At this point, I only need to run `brew services restart ollama` without setting any additional environment variables, and ollama will correctly perform parallel output. I'm not entirely sure if I have set it up correctly. What should the correct method for persistently setting ollama's environment variables be? My `~/Library/LaunchAgents/environments.plist` is as follows: ``` <?xml version="1.0" encoding="UTF-8"?> <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd"> <plist version="1.0"> <dict> <key>Label</key> <string>environment.variables.user</string> <key>ProgramArguments</key> <array> <string>/bin/sh</string> <string>-c</string> <string> /bin/launchctl setenv OLLAMA_NUM_PARALLEL 4; /bin/launchctl setenv OLLAMA_MAX_LOADED_MODELS 4; </string> </array> <key>RunAtLoad</key> <true/> </dict> </plist> ``` ### Relevant log output ```shell ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.12.9
GiteaMirror added the bug label 2026-04-22 17:46:29 -05:00
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#34323
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?