Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Shut up CUDA prints #326

Closed
wants to merge 1 commit into from
Closed

Shut up CUDA prints #326

wants to merge 1 commit into from

Conversation

LoganDark
Copy link
Contributor

These are really annoying. Maybe keep them for debugging, but don't clutter up every application's stderr unconditionally. Was too lazy to add a specific check for that, just wanted this out of my console as fast as possible, but may need to polish up the PR a bit before merging.

Fixes #271

@LoganDark
Shut up CUDA prints
8ccb99c 
These are really, really annoying. Maybe keep them for debugging,
but don't clutter up every application's stderr unconditionally...
@ring-c
Copy link

ring-c commented May 10, 2024

We have even more offenders on this issue, my logs looks like this

ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4080, compute capability 8.9, VMM: yes
ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 2.56 MiB
ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 8.58 MiB
ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 2.56 MiB
ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 8.58 MiB
ggml_gallocr_reserve_n: reallocating CUDA0 buffer from size 0.00 MiB to 515.52 MiB

and reallocating CUDA0 buffer from size keeps spamming.

@LoganDark
Copy link
Contributor Author

@ring-c those prints did not exist back in 2023 when I opened this PR :)

@LoganDark LoganDark closed this May 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

don't print in ggml_init_cublas
2 participants
@LoganDark @ring-c