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 #8181] Does Ollama prioritize the use of shared GPU memory? #51734

New Issue
Closed
opened 2026-04-28 20:49:38 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 20:49:38 -05:00
Owner
Copy Link

Originally created by @mydreamworldpolly on GitHub (Dec 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8181

What is the issue?

I installed ollama 0.5.1 and try the new settings
OLLAMA_FLASH_ATTENTION=1
OLLAMA_KV_CACHE_TYPE=q8_0
and use Qwen2.5-7b Q4 with long context 130000. The VRAM usage has indeed decreased as expected, but Ollama still occupies shared memory instead of fully utilizing the freed-up VRAM, resulting in performance degradation.
155617

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.5.1

Originally created by @mydreamworldpolly on GitHub (Dec 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8181 ### What is the issue? I installed ollama 0.5.1 and try the new settings OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 and use Qwen2.5-7b Q4 with long context 130000. The VRAM usage has indeed decreased as expected, but Ollama still occupies shared memory instead of fully utilizing the freed-up VRAM, resulting in performance degradation. <img width="360" alt="155617" src="https://github.com/user-attachments/assets/007fd6e4-1ba9-4d50-8474-9f1b967f9b1d" /> ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.1
GiteaMirror added the bug label 2026-04-28 20:49:38 -05:00
GiteaMirror commented 2026-04-28 20:49:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 20, 2024):

https://github.com/ollama/ollama/issues/6160

<!-- gh-comment-id:2556558497 --> @rick-github commented on GitHub (Dec 20, 2024): https://github.com/ollama/ollama/issues/6160
GiteaMirror commented 2026-04-28 20:49:44 -05:00
Author
Owner
Copy Link

@mydreamworldpolly commented on GitHub (Dec 20, 2024):

#6160

solved. Thank you!

<!-- gh-comment-id:2556594395 --> @mydreamworldpolly commented on GitHub (Dec 20, 2024): > #6160 solved. Thank you!
GiteaMirror commented 2026-04-28 20:49:46 -05:00
Author
Owner
Copy Link

@mydreamworldpolly commented on GitHub (Dec 20, 2024):

closed

<!-- gh-comment-id:2556595004 --> @mydreamworldpolly commented on GitHub (Dec 20, 2024): closed
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#51734
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?