ouhang

cuda_helper.cu:82: void helperSetBroadcastableTensorDescriptor(const taso::Tensor&, const taso::Tensor&, cudnnTensorDescriptor_t): Assertion `false' failed.

1

Just as the title: (gdb) p input $1 = (const taso::Tensor &) @0x555589dcf678: {static MAX_KEY_LENGTH = 274, static MAGIC_NUMBER = 23333, numDim = 1, dim = {1, -2008300352, 21845, -1980118144,...

CUDNN failure: CUDNN_STATUS_BAD_PARAM TASO/src/cudnn/element_kernel.cu:193

1

Just as the title: CUDNN failure: CUDNN_STATUS_BAD_PARAM /disk2/ouhang.oh/experiment/TASO/src/cudnn/element_kernel.cu:193 The op is OP_EW_MUL ele->inputs[0] $12 = {static MAX_KEY_LENGTH = 274, static MAGIC_NUMBER = 23333, numDim = 4, dim = {1, 64,...

I think further substitution may be generated if we can fix "Cannot find input tensor" and "unsupported" issue. Below is the log: Found unsupported ONNX operator: LRN (Skipped) Cannot find...

output length mismatch and no attr

1

for op: input: "conv1" input: "Pad_pads" input: "Pad_value" output: "legacy_padded_tensor" name: "Pad" op_type: "Pad" domain: "" Below assertion fails: outputs = xf_operators[op.op_type](op, graph, tensors, model.graph.initializer) if not isinstance(outputs, list): outputs...

When weight_initial is NULL then new_weight will fail

4

In ops.cc method new_weight, current logic is when weight_initial != NULL, then allocate_memory, else weight_ptr would be null ptr. I don't know whether this logic is what we wanted, but...

什么时候支持通义千问或者要用千问怎么用？ When will it support tongyi?

1

Just as the title.