Replies: 1 comment 1 reply
-
|
Yes, but will wait for upstream glslang to support int8 dot product extension |
Beta Was this translation helpful? Give feedback.
1 reply
-
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Do we plan to make the quantized model int8 run on the Vulkan backend? Especially generative AI models are very slow and need extremely fast technique to run on Vulkan device
Beta Was this translation helpful? Give feedback.
All reactions