github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10795] gpu没有跑满，是否可以将剩余的gpu全部用来提升模型的推理速度 #53600

New Issue
Closed
opened 2026-04-29 04:07:56 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-29 04:07:56 -05:00
Owner
Copy Link

Originally created by @valueLzy on GitHub (May 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10795

Image Image
Originally created by @valueLzy on GitHub (May 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10795 <img width="665" alt="Image" src="https://github.com/user-attachments/assets/94d88f00-48b2-4a01-8c37-e18e64c13fed" /> <img width="456" alt="Image" src="https://github.com/user-attachments/assets/d2d95834-1030-4427-bf7b-a26beddbfc3f" />
GiteaMirror added the question label 2026-04-29 04:07:56 -05:00
GiteaMirror commented 2026-04-29 04:08:23 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

You can increase the memory usage by increasing the size of the context buffer, but it won't speed up inference.

<!-- gh-comment-id:2897214780 --> @rick-github commented on GitHub (May 21, 2025): You can increase the memory usage by increasing the size of the [context buffer](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size), but it won't speed up inference.
GiteaMirror commented 2026-04-29 04:08:26 -05:00
Author
Owner
Copy Link

@valueLzy commented on GitHub (May 21, 2025):

您可以通过增加上下文缓冲区的大小来增加内存使用量，但这不会加快推理速度。

谢谢指导，后续会有加快推理速度的功能计划吗

<!-- gh-comment-id:2897232084 --> @valueLzy commented on GitHub (May 21, 2025): > [您可以通过增加上下文缓冲区](https://github.com/ollama/ollama/blob/main/docs/faq.md#how-can-i-specify-the-context-window-size)的大小来增加内存使用量，但这不会加快推理速度。 谢谢指导，后续会有加快推理速度的功能计划吗
GiteaMirror commented 2026-04-29 04:08:28 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 21, 2025):

There are always plans to improve performance, but your model is already 100% loaded in GPU, so there's not much room for improvement.

<!-- gh-comment-id:2897438575 --> @rick-github commented on GitHub (May 21, 2025): There are always plans to improve performance, but your model is already 100% loaded in GPU, so there's not much room for improvement.
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 question
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#53600
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?