github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1864] loading the model into GPU direct #63103

New Issue
Closed
opened 2026-05-03 12:06:39 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 12:06:39 -05:00
Owner
Copy Link

Originally created by @Mahmuod1 on GitHub (Jan 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1864

there is any way to loading the llm model into the GPU memory direct not in CPU and then switch in GPU as i seen in monitor

Originally created by @Mahmuod1 on GitHub (Jan 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1864 there is any way to loading the llm model into the GPU memory direct not in CPU and then switch in GPU as i seen in monitor
GiteaMirror commented 2026-05-03 12:06:42 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 9, 2024):

This is essentially what Ollama does. It tries to offload as many layers of the model as possible into the GPU, and then if there is not enough space, will load the rest into memory. In order to load the model into the GPU's memory though, your computer has to use at least some memory from your system to read it and perform the copy. With a Mac, since it has Unified Memory, you don't have to copy the model through the system memory.

Are you having problems with something in particular though? Do you have less system memory than GPU memory?

<!-- gh-comment-id:1883606139 --> @pdevine commented on GitHub (Jan 9, 2024): This is essentially what Ollama does. It tries to offload as many layers of the model as possible into the GPU, and then if there is not enough space, will load the rest into memory. In order to load the model into the GPU's memory though, your computer has to use at least _some_ memory from your system to read it and perform the copy. With a Mac, since it has Unified Memory, you don't have to copy the model through the system memory. Are you having problems with something in particular though? Do you have less system memory than GPU memory?
GiteaMirror commented 2026-05-03 12:06:45 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 11, 2024):

Going to go ahead and close out the issue.

<!-- gh-comment-id:1989376820 --> @pdevine commented on GitHub (Mar 11, 2024): Going to go ahead and close out 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
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#63103
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?