github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4792] Added the ability to configure maxvram per GPU when there are multiple GPUs #49532

New Issue
Closed
opened 2026-04-28 12:07:40 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 12:07:40 -05:00
Owner
Copy Link

Originally created by @hamkido on GitHub (Jun 3, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4792

Originally assigned to: @dhiltgen on GitHub.

Current can config MaxVRAM, but can not config per gpu maxvram when have dual gpu.

Originally created by @hamkido on GitHub (Jun 3, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4792 Originally assigned to: @dhiltgen on GitHub. Current can config MaxVRAM, but can not config per gpu maxvram when have dual gpu.
GiteaMirror added the feature request label 2026-04-28 12:07:40 -05:00
GiteaMirror commented 2026-04-28 12:07:43 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 18, 2024):

With 0.1.45 we'll now be aware of VRAM skew between multiple GPUs and should allocate the layers proportionally to what is available on each GPU. While this doesn't address your feature request, hopefully you'll see better behavior on multiple GPUs with this new release.

<!-- gh-comment-id:2177103794 --> @dhiltgen commented on GitHub (Jun 18, 2024): With 0.1.45 we'll now be aware of VRAM skew between multiple GPUs and should allocate the layers proportionally to what is available on each GPU. While this doesn't address your feature request, hopefully you'll see better behavior on multiple GPUs with this new release.
GiteaMirror commented 2026-04-28 12:07:44 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 3, 2024):

Please give the latest release a try and if you see it get the memory prediction incorrect between your skewed VRAM GPUs share your server log and I'll reopen the issue.

<!-- gh-comment-id:2207484832 --> @dhiltgen commented on GitHub (Jul 3, 2024): Please give the latest release a try and if you see it get the memory prediction incorrect between your skewed VRAM GPUs share your server log and I'll reopen the issue.
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 feature request
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#49532
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?