num_beams less than 5 not working?
#6
by kdcyberdude - opened
Using num_beams less than 5, gives this error? Can anyone explain why that is the case here?
/opt/conda/conda-bld/pytorch_1729647382455/work/aten/src/ATen/native/cuda/IndexKernel.cu:93: operator(): block: [2,0,0], thread: [32,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1