ERROR in app: Exception on /api/fillblank [POST]
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 2070, in wsgi_app
response = self.full_dispatch_request()
File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1515, in full_dispatch_request
rv = self.handle_user_exception(e)
File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1513, in full_dispatch_request
rv = self.dispatch_request()
File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1499, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**req.view_args)
File "main.py", line 66, in fillBlank
result = fillblank.fillBlank(model)
File "/app/controller/fill_blank_controller.py", line 18, in fillBlank
presence_penalty = presence_penalty1)
File "/usr/local/lib/python3.6/dist-packages/bminf/models/cpm2.py", line 151, in fill_blank
frequency_penalty, presence_penalty, 0)
File "/usr/local/lib/python3.6/dist-packages/bminf/models/cpm2.py", line 103, in pre_processing
ctx = self.encode(np.array([idx], dtype=np.int64), [input_length])
File "/usr/local/lib/python3.6/dist-packages/bminf/arch/t5/model.py", line 238, in encode
True
File "/usr/local/lib/python3.6/dist-packages/bminf/layers/transformer_block.py", line 42, in forward
x = self.self_attention.forward(allocator, x, attention_mask, self_attn_position_bias)
File "/usr/local/lib/python3.6/dist-packages/bminf/layers/attention.py", line 63, in forward
qkv_i32
File "/usr/local/lib/python3.6/dist-packages/bminf/functions/gemm.py", line 86, in igemm
_igemm(allocator, a, aT, b, bT, c, device, stream)
File "/usr/local/lib/python3.6/dist-packages/bminf/functions/gemm.py", line 180, in _igemm
cublasLt.checkCublasStatus( cublasLt.cublasLtMatrixTransform(lthandle, transform_desc_b, ctypes.byref(v1), b.data.ptr, layout_b, ctypes.byref(v0), 0, 0, trans_b.ptr, layout_trans_b, stream.ptr) )
File "/usr/local/lib/python3.6/dist-packages/bminf/backend/cublaslt.py", line 101, in checkCublasStatus
raise RuntimeError("cublas error: %s" % cublas_errors[cublas_status])
RuntimeError: cublas error: CUBLAS_STATUS_NOT_SUPPORTED
ERROR in app: Exception on /api/fillblank [POST] Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 2070, in wsgi_app response = self.full_dispatch_request() File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1515, in full_dispatch_request rv = self.handle_user_exception(e) File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1513, in full_dispatch_request rv = self.dispatch_request() File "/usr/local/lib/python3.6/dist-packages/flask/app.py", line 1499, in dispatch_request return self.ensure_sync(self.view_functions[rule.endpoint])(**req.view_args) File "main.py", line 66, in fillBlank result = fillblank.fillBlank(model) File "/app/controller/fill_blank_controller.py", line 18, in fillBlank presence_penalty = presence_penalty1) File "/usr/local/lib/python3.6/dist-packages/bminf/models/cpm2.py", line 151, in fill_blank frequency_penalty, presence_penalty, 0) File "/usr/local/lib/python3.6/dist-packages/bminf/models/cpm2.py", line 103, in pre_processing ctx = self.encode(np.array([idx], dtype=np.int64), [input_length]) File "/usr/local/lib/python3.6/dist-packages/bminf/arch/t5/model.py", line 238, in encode True File "/usr/local/lib/python3.6/dist-packages/bminf/layers/transformer_block.py", line 42, in forward x = self.self_attention.forward(allocator, x, attention_mask, self_attn_position_bias) File "/usr/local/lib/python3.6/dist-packages/bminf/layers/attention.py", line 63, in forward qkv_i32 File "/usr/local/lib/python3.6/dist-packages/bminf/functions/gemm.py", line 86, in igemm _igemm(allocator, a, aT, b, bT, c, device, stream) File "/usr/local/lib/python3.6/dist-packages/bminf/functions/gemm.py", line 180, in _igemm cublasLt.checkCublasStatus( cublasLt.cublasLtMatrixTransform(lthandle, transform_desc_b, ctypes.byref(v1), b.data.ptr, layout_b, ctypes.byref(v0), 0, 0, trans_b.ptr, layout_trans_b, stream.ptr) ) File "/usr/local/lib/python3.6/dist-packages/bminf/backend/cublaslt.py", line 101, in checkCublasStatus raise RuntimeError("cublas error: %s" % cublas_errors[cublas_status]) RuntimeError: cublas error: CUBLAS_STATUS_NOT_SUPPORTED