Open heiheiheibj opened 1 week ago
ptxas C:\Users\ADMINI~1\AppData\Local\Temp\tmpsgwrczog.ptx, line 5; fatal : Unsupported .version 8.6; current version is '8.5' ptxas fatal : Ptx assembly aborted due to errors Traceback (most recent call last): File "D:\ProgramData\anaconda3\envs\cuda\Lib\site-packages\triton\backends\nvidia\compiler.py", line 295, in make_cubin subprocess.run(ptxas_cmd, check=True, close_fds=False, stderr=flog) File "D:\ProgramData\anaconda3\envs\cuda\Lib\subprocess.py", line 569, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin\ptxas.exe', '-lineinfo', '-v', '--gpu-name=sm_86', 'C:\Users\ADMINI~1\AppData\Local\Temp\tmpsgwrczog.ptx', '-o', 'C:\Users\ADMINI~1\AppData\Local\Temp\tmpsgwrczog.ptx.o']' returned non-zero exit status 4294967295.
Triton on windows is hard to make it work. I think Unsloth team doesn't have OS windows to test this too. Perhaps you can use WSL to do Unsloth stuff .-.
os: WINDOWS 10
File "D:\unsloth\unsloth\kernels\rms_layernorm.py", line 144, in forward fx[(n_rows,)]( File "D:\ProgramData\anaconda3\envs\cuda\Lib\site-packages\triton\runtime\jit.py", line 345, in
return lambda *args, *kwargs: self.run(grid=grid, warmup=False, args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ProgramData\anaconda3\envs\cuda\Lib\site-packages\triton\runtime\jit.py", line 662, in run
kernel = self.compile(
^^^^^^^^^^^^^
File "D:\ProgramData\anaconda3\envs\cuda\Lib\site-packages\triton\compiler\compiler.py", line 286, in compile
next_module = compile_ir(module, metadata)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ProgramData\anaconda3\envs\cuda\Lib\site-packages\triton\backends\nvidia\compiler.py", line 329, in
stages["cubin"] = lambda src, metadata: self.make_cubin(src, metadata, options, self.capability)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ProgramData\anaconda3\envs\cuda\Lib\site-packages\triton\backends\nvidia\compiler.py", line 309, in make_cubin
raise RuntimeError(f'
ptxas
failed with error code {e.returncode}: \n{log}') RuntimeError:ptxas
failed with error code 4294967295:thx