feat: change minimal supported CUDA version to 11.7 (Dao-AILab#1206)

Author: jue-jue-zi

README.md

@@ -98,7 +98,7 @@ MAX_JOBS=4 pip install flash-attn --no-build-isolation
 
 ### NVIDIA CUDA Support
 **Requirements:**
-- CUDA 11.6 and above.
+- CUDA 11.7 and above.
 
 We recommend the
 [Pytorch](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch)

setup.py

@@ -156,9 +156,9 @@ def validate_and_update_archs(archs):
     cc_flag = []
     if CUDA_HOME is not None:
         _, bare_metal_version = get_cuda_bare_metal_version(CUDA_HOME)
-        if bare_metal_version < Version("11.6"):
+        if bare_metal_version < Version("11.7"):
             raise RuntimeError(
-                "FlashAttention is only supported on CUDA 11.6 and above.  "
+                "FlashAttention is only supported on CUDA 11.7 and above.  "
                 "Note: make sure nvcc has a supported version by running nvcc -V."
             )
     # cc_flag.append("-gencode")