github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #9620] Compute Capability 3.7 still needed #32037

New Issue
Closed
opened 2026-04-22 12:54:42 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 12:54:42 -05:00
Owner
Copy Link

Originally created by @cbureriu on GitHub (Mar 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9620

I understand that CC 3.7 is outdated, but I have a specific requirement for K80 cards. Previously, Ollama could be patched for CC 3.5 and 3.7. If there's still a way to make this work, I would greatly appreciate any workaround.

Originally created by @cbureriu on GitHub (Mar 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9620 I understand that CC 3.7 is outdated, but I have a specific requirement for K80 cards. Previously, Ollama could be patched for CC 3.5 and 3.7. If there's still a way to make this work, I would greatly appreciate any workaround.
GiteaMirror added the feature request label 2026-04-22 12:54:42 -05:00
GiteaMirror commented 2026-04-22 12:54:44 -05:00
Author
Owner
Copy Link

@dogkeeper886 commented on GitHub (Apr 8, 2025):

I understand that CC 3.7 is outdated, but I have a specific requirement for K80 cards. Previously, Ollama could be patched for CC 3.5 and 3.7. If there's still a way to make this work, I would greatly appreciate any workaround.

This closed issue (https://github.com/ollama/ollama/issues/1756) details the implementation of support for 3.7. A fork of the ollama repository (https://github.com/idream3000/ollama37.git) includes the commits you referenced, which modify the files necessary to support. This fork has been tested and can successfully run models like phi-4 and DeepSeek-R1 on a K80 GPU.

<!-- gh-comment-id:2785299402 --> @dogkeeper886 commented on GitHub (Apr 8, 2025): > I understand that CC 3.7 is outdated, but I have a specific requirement for K80 cards. Previously, Ollama could be patched for CC 3.5 and 3.7. If there's still a way to make this work, I would greatly appreciate any workaround. This closed issue (https://github.com/ollama/ollama/issues/1756) details the implementation of support for 3.7. A fork of the ollama repository (https://github.com/idream3000/ollama37.git) includes the commits you referenced, which modify the files necessary to support. This fork has been tested and can successfully run models like phi-4 and DeepSeek-R1 on a K80 GPU.
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#32037
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?