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 #4064] Support DirectML #2524

New Issue
Open
opened 2026-04-12 12:50:56 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-12 12:50:56 -05:00
Owner
Copy Link

Originally created by @shawnshi on GitHub (Apr 30, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4064

Will you support DirectML.

Originally created by @shawnshi on GitHub (Apr 30, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4064 Will you support DirectML.
GiteaMirror added the feature request label 2026-04-12 12:50:56 -05:00
GiteaMirror commented 2026-04-12 12:50:57 -05:00
Author
Owner
Copy Link

@psython123 commented on GitHub (Jun 19, 2024):

I second this question/request.

<!-- gh-comment-id:2177727498 --> @psython123 commented on GitHub (Jun 19, 2024): I second this question/request.
GiteaMirror commented 2026-04-12 12:50:57 -05:00
Author
Owner
Copy Link

@oscarbg commented on GitHub (Jul 31, 2024):

+1 will add support simultaneously for new Intel and Qualcomm SOCs with 40+ tops NPUs

<!-- gh-comment-id:2261604141 --> @oscarbg commented on GitHub (Jul 31, 2024): +1 will add support simultaneously for new Intel and Qualcomm SOCs with 40+ tops NPUs
GiteaMirror commented 2026-04-12 12:50:58 -05:00
Author
Owner
Copy Link

@fanlessfan commented on GitHub (Sep 25, 2024):

+1

<!-- gh-comment-id:2375309670 --> @fanlessfan commented on GitHub (Sep 25, 2024): +1
GiteaMirror commented 2026-04-12 12:50:58 -05:00
Author
Owner
Copy Link

@CutterSol commented on GitHub (Feb 12, 2025):

+1

DirectML is for GPUs that can run DX12 or higher.. Sets a standard for Windows based systems (supporting DX12 or higher GPUs) and adds compatibility for a lot of GPUs, rather than trying all sorts of workarounds and sorting through tons of post, often with no results.

<!-- gh-comment-id:2652612386 --> @CutterSol commented on GitHub (Feb 12, 2025): +1 DirectML is for GPUs that can run DX12 or higher.. Sets a standard for Windows based systems (supporting DX12 or higher GPUs) and adds compatibility for a lot of GPUs, rather than trying all sorts of workarounds and sorting through tons of post, often with no results.
GiteaMirror commented 2026-04-12 12:50:58 -05:00
Author
Owner
Copy Link

@Alexamenus commented on GitHub (Mar 24, 2025):

would like this too

<!-- gh-comment-id:2748576010 --> @Alexamenus commented on GitHub (Mar 24, 2025): would like this too
GiteaMirror commented 2026-04-12 12:50:59 -05:00
Author
Owner
Copy Link

@Tim-Gabrikowski commented on GitHub (Oct 18, 2025):

I would love it too. GPU or maybe even NPU support for windwos would be an absolute game changer for me!

<!-- gh-comment-id:3418060230 --> @Tim-Gabrikowski commented on GitHub (Oct 18, 2025): I would love it too. GPU or maybe even NPU support for windwos would be an absolute game changer for me!
GiteaMirror commented 2026-04-12 12:50:59 -05:00
Author
Owner
Copy Link

@Quazonish commented on GitHub (Dec 19, 2025):

Any updates?

<!-- gh-comment-id:3676003418 --> @Quazonish commented on GitHub (Dec 19, 2025): Any updates?
GiteaMirror commented 2026-04-12 12:50:59 -05:00
Author
Owner
Copy Link

@CutterSol commented on GitHub (Dec 20, 2025):

These people are Nvidia fanboys. They've changed a lot about the program in a little over a year, seem to be moving away from local LLMs and failed to address supporting GPUs that a large number of users have while making those changes--Steam surveys are not key to user percentage. I've moved on to LM Studio and better solutions. Too much of a hassle to really get Ollama working once you notice you're getting CPU inference only...

<!-- gh-comment-id:3677320808 --> @CutterSol commented on GitHub (Dec 20, 2025): These people are Nvidia fanboys. They've changed a lot about the program in a little over a year, seem to be moving away from local LLMs and failed to address supporting GPUs that a large number of users have while making those changes--Steam surveys are not key to user percentage. I've moved on to LM Studio and better solutions. Too much of a hassle to really get Ollama working once you notice you're getting CPU inference only...
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#2524
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?