-
Notifications
You must be signed in to change notification settings - Fork 8.5k
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.
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
Vulkan backend fails to compile a number of shaders on Adreno #6395
Comments
And in the shader validation errors category (in other shaders, that compiled without errors despite those):
and
storageBuffer8BitAccess is not exposed in this particular Adreno. and other ones:
|
I get much further when using Kompute with some hacks to skip feature probing/checks that we're on Vulkan 1.2 or above. Using:
but only f16 works there, not q4_0 (tested with https://huggingface.co/ggml-org/models/blob/main/tinyllama-1.1b/ggml-model-f16.gguf) |
While I don't have the time to figure out Adreno support myself, I'm happy to assist if someone wants to take it on. The lack of |
This issue was closed because it has been inactive for 14 days since being marked as stale. |
Hello,
Tried to run llama.cpp with Vulkan on Adreno 690 (Snapdragon 8cx Gen 3) on Windows 11 version 24H2 and this is what I get:
When uncommenting shaders it turned out that the problematic ones also included
dequant_q4_0
among other ones.This is bug #5739 on Android.
The text was updated successfully, but these errors were encountered: