Skip to content

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1 - #1920

Closed
sstamenk wants to merge 4 commits into
bitsandbytes-foundation:mainfrom
sstamenk:rocm-4bit-kernel-optimization
Closed

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1#1920
sstamenk wants to merge 4 commits into
bitsandbytes-foundation:mainfrom
sstamenk:rocm-4bit-kernel-optimization

Implement correct fp32 access pattern

9a8712d
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning

The logs for this run have expired and are no longer available.