Closed lljbash closed 6 months ago
InternEVO uses FlashAttention 2.2.1, where the CUDA module is renamed from flash_attn_cuda to flash_attn_2_cuda. This commit mocks the correct module name.
InternEVO uses FlashAttention 2.2.1, where the CUDA module is renamed from flash_attn_cuda to flash_attn_2_cuda. This commit mocks the correct module name.