FlashAttention-2 support
#7
by
afaulconbridge - opened
Please add FlashAttention-2 support https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2
Feel free to open an issue on Github
Please add FlashAttention-2 support https://huggingface.co/docs/transformers/perf_infer_gpu_one#flashattention-2
Feel free to open an issue on Github