Skip to content

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1 #228

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

[ROCm] Optimize kgemm_4bit_inference_naive for ROCm, use it for batch sizes other than 1 #228

Annotations

1 warning

CUDA (windows, T4, 11.8.0, 2.7.1, https://download.pytorch.org/whl/cu118)  /  build

succeeded Apr 13, 2026 in 3m 45s