github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5496] why GGML_CUDA_FORCE_MMQ is yes and CUDA_USE_TENSOR_CORES is no #3439

New Issue
Closed
opened 2026-04-12 14:06:19 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:06:19 -05:00
Owner
Copy Link

Originally created by @rabbitpig on GitHub (Jul 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5496

Hi:

I am a newbie and curious about how these configs come out.

image

Someone can tell me how to chane these.

Thanks.

Originally created by @rabbitpig on GitHub (Jul 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5496 Hi: I am a newbie and curious about how these configs come out. ![image](https://github.com/ollama/ollama/assets/2839943/699df0ca-4d48-48e8-9fcb-ff081fb1ed12) Someone can tell me how to chane these. Thanks.
GiteaMirror added the question label 2026-04-12 14:06:19 -05:00
GiteaMirror commented 2026-04-12 14:06:21 -05:00
Author
Owner
Copy Link

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

This actually comes from llama.cpp, which is the inference backend used by ollama

<!-- gh-comment-id:2373483930 --> @egeres commented on GitHub (Sep 25, 2024): This actually comes from llama.cpp, which is the inference backend used by ollama
GiteaMirror commented 2026-04-12 14:06:22 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 24, 2024):

The compiler flags for llama.cpp are defined in the Ollama build. With the new Go server, see llama.go and the makefiles

Development instructions are here - https://github.com/ollama/ollama/blob/main/docs/development.md#transition-to-go-runner

<!-- gh-comment-id:2434118964 --> @dhiltgen commented on GitHub (Oct 24, 2024): The compiler flags for llama.cpp are defined in the Ollama build. With the new Go server, see [llama.go](https://github.com/ollama/ollama/blob/main/llama/llama.go) and the [makefiles](https://github.com/ollama/ollama/tree/main/llama/make) Development instructions are here - https://github.com/ollama/ollama/blob/main/docs/development.md#transition-to-go-runner
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#3439
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?