编译模型的时候出现error: failed to legalize operation 'MGB.ConvBias'
- Dominant language
- C++
- Stars
- 483
- Forks
- 56
- PR merge metrics
- No merged PRs in 30d
Description
dump代码如下
@jit.trace(symbolic=True, capture_as_const=True)
def fun(data, *, net):
pred = net(data)
return pred
fun(data, net=model)
fun.dump("test.mge", arg_names=["data"],optimize_for_inference=False, enable_fuse_conv_bias_nonlinearity=False, enable_fuse_conv_bias_with_z=False)
Contributor guide
No contributing guide indexed for this repository
Research direction
Start with the provided jit.trace and fun.dump reproduction, then search the compiler for legalization handling of the 'MGB.ConvBias' operation. Reproduce the failure with the listed fusion options and trace where legalization stops; done means the shown model compiles successfully or the unsupported operation is reported with a clear resolution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, machine-learning
- Domain
- compilers, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 30/100