Triton Issue with flash_attn.layers.rotary.apply_rotary_emb_qkv_

[albertotono]

I am getting this error /usr/bin/gcc /tmp/tmp2wi5s8nw/main.c -O3 -I/opt/.venv/lib/python3.10/site-packages/triton/common/../third_party/cuda/include -I/usr/local/include/python3.10 -I/tmp/tmp2wi5s8nw -shared -fPIC -lcuda -o /tmp/tmp2wi5s8nw/rotary_kernel.cpython-310-x86_64-linux-gnu.so -L/usr/lib/x86_64-linux-gnu

> <string>", line 63, in rotary_kernel
>   File "/opt/.venv/lib/python3.10/site-packages/triton/compiler/compiler.py", line 425, in compile
>     so_path = make_stub(name, signature, constants)
>   File "/opt/.venv/lib/python3.10/site-packages/triton/compiler/make_launcher.py", line 39, in make_stub
>     so = _build(name, src_path, tmpdir)
>   File "/opt/.venv/lib/python3.10/site-packages/triton/common/build.py", line 90, in _build
>     ret = subprocess.check_call(cc_cmd)
>   File "/usr/local/lib/python3.10/subprocess.py", line 369, in check_call
>     raise CalledProcessError(retcode, cmd)
> subprocess.CalledProcessError: Command '['/usr/bin/gcc', '/tmp/tmp8yd51al2/main.c', '-O3', '-I/opt/.venv/lib/python3.10/site-packages/triton/common/../third_party/cuda/include',