Skip to content

Add documentation about CLBlast #1604

New issue

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

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

Already on GitHub? # to your account

Merged
merged 2 commits into from
May 27, 2023
Merged

Add documentation about CLBlast #1604

merged 2 commits into from
May 27, 2023

Conversation

SlyEcho
Copy link
Collaborator

@SlyEcho SlyEcho commented May 26, 2023

Installing, compiling and using CLBlast

Relevant issue: #1546

SlyEcho added 2 commits May 27, 2023 00:30
@arch-btw
Copy link
Contributor

Thank you! Just a heads up for those on older AMD devices, I got a step further by adding:

ROC_ENABLE_PRE_VEGA=1

For example without ROC_ENABLE_PRE_VEGA=1 it outputs:

ggml_opencl: selected platform 'AMD Accelerated Parallel Processing' does not have any devices.

And with ROC_ENABLE_PRE_VEGA=1 it outputs:

ggml_opencl: selecting platform: 'AMD Accelerated Parallel Processing'
ggml_opencl: selecting device: 'gfx803'
ggml_opencl: device FP16 support: true

Granted, now I ran into this issue, but I think that's unrelated:

ggml_opencl: (queue = clCreateCommandQueue(context, device, CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE, &err), (err != CL_INVALID_QUEUE_PROPERTIES && err != CL_INVALID_VALUE ? err : (queue = clCreateCommandQueue(context, device, 0, &err), err) )) error -6 at ggml-opencl.cpp:490

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants