David Huang edd1d8686a HIP: implement FlashAttention via rocWMMA for CDNA and RDNA3+ (llama/12032)
Adds GGML_HIP_ROCWMMA_FATTN and rocwmma header check
Adds rocWMMA support to fattn-wmma-f16
2025-03-08 15:13:01 +02:00
..