How can deploy this model

#20
by yongho1213 - opened

I'm deploy this model using tgi.
but it shown bellow error.(using A100 80GB*2)
../aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [842,0,0], thread: [32,0,0] Assertion srcIndex < srcSelectDimSize failed.
../aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [842,0,0], thread: [33,0,0] Assertion srcIndex < srcSelectDimSize failed.
../aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [842,0,0], thread: [34,0,0] Assertion srcIndex < srcSelectDimSize failed.
../aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [842,0,0], thread: [35,0,0] Assertion srcIndex < srcSelectDimSize failed.
../aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [842,0,0], thread: [36,0,0] Assertion srcIndex < srcSelectDimSize failed.
../aten/src/ATen/native/cuda/Indexing.cu:1146: indexSelectLargeIndex: block: [842,0,0], thread: [37,0,0] Assertion srcIndex < srcSelectDimSize failed.

Please share deploy code.

Sign up or log in to comment