github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8635] Use of System Ram over RDMA in GPU to allow for GPU acceleration on lower VRAM hardware. #67648

New Issue
Open
opened 2026-05-04 11:12:28 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-04 11:12:28 -05:00
Owner
Copy Link

Originally created by @SlinkierElm5611 on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8635

Hi all!

I'm a GPU dev who has been messing around with Ollama for some self hosting. I was wondering if there is any reason Ollama has not been able to take advantage of GPU acceleration while using system RAM through RDMA(reBar). I have done system ram access through RDMA on GPU for real time processing and have had better results than CPU side tasks despite the increase in data latency when going over PCIE.

I look forward to hearing from you!

Originally created by @SlinkierElm5611 on GitHub (Jan 28, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8635 Hi all! I'm a GPU dev who has been messing around with Ollama for some self hosting. I was wondering if there is any reason Ollama has not been able to take advantage of GPU acceleration while using system RAM through RDMA(reBar). I have done system ram access through RDMA on GPU for real time processing and have had better results than CPU side tasks despite the increase in data latency when going over PCIE. I look forward to hearing from you!
GiteaMirror added the feature request label 2026-05-04 11:12:28 -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 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#67648
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?