llama.cpp
Fix Vulkan Quantized Matrix Vector Multiplication on AMD GPUs when ncols < 64
#8855
Merged
Merged
Fix Vulkan Quantized Matrix Vector Multiplication on AMD GPUs when ncols < 64 #8855
ggerganov
merged
2 commits into
master
from
0cc4m/vulkan-fix-mmv-tests
Fix Vulkan mul mat vec invalid results when ncols < warp size
ecabd54d
Only run backend ops mul mat vec block size test if block size not al…
6c75cb95
0cc4m
changed the title 
0cc4m
changed the title 
ggerganov
approved these changes
on 2024-08-05
Login to write a write a comment.
Login via GitHub