github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[PR #10700] Estimate projector memory correctly for Ollama engine #13332

New Issue
Closed
opened 2026-04-13 00:24:07 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-13 00:24:07 -05:00
Owner
Copy Link

Original Pull Request: https://github.com/ollama/ollama/pull/10700

State: closed
Merged: Yes

The Llama engine always places vision projectors on the first GPU if one exists. However, the Ollama engine groups it with the output layer, which means the projector is only offloaded if all other layers are offloaded. The memory estimation code always assumes the former layout - this changes it to use the correct layout based on the engine.

This addresses two impacts of the current behavior:

  • In multi-GPU setups, we can crash with OOM errors when we try to allocate memory on a full GPU while another still has space.
  • If the vision projector is large, it may prevent us from offloading anything when we could have fit some of the text layers.
**Original Pull Request:** https://github.com/ollama/ollama/pull/10700 **State:** closed **Merged:** Yes --- The Llama engine always places vision projectors on the first GPU if one exists. However, the Ollama engine groups it with the output layer, which means the projector is only offloaded if all other layers are offloaded. The memory estimation code always assumes the former layout - this changes it to use the correct layout based on the engine. This addresses two impacts of the current behavior: - In multi-GPU setups, we can crash with OOM errors when we try to allocate memory on a full GPU while another still has space. - If the vision projector is large, it may prevent us from offloading anything when we could have fit some of the text layers.
GiteaMirror added the pull-request label 2026-04-13 00:24:07 -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 pull-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#13332
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?