mlc-ai / mlc-ai/web-stable-diffusion
raise TypeError(f"Please convert {rhs} with `const` first")
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 3.7k
- Forks
- 238
- PR merge metrics
- No merged PRs in 30d
Description
while loading model ,get
text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
Traceback (most recent call last):
File "/srv/workspace/anaconda3/envs/web_sd/lib/python3.9/site-packages/torch/_dynamo/output_graph.py", line 670, in call_user_compiler
compiled_fn = compiler_fn(gm, self.fake_example_inputs())
File "/srv/workspace/anaconda3/envs/web_sd/lib/python3.9/site-packages/torch/_dynamo/debug_utils.py", line 1055, in debug_wrapper
compiled_gm = compiler_fn(gm, example_inputs)
File "/srv/workspace/framework/tvm/python/tvm/relax/frontend/torch/dynamo.py", line 151, in _capture
mod_ = from_fx(
File "/srv/workspace/framework/tvm/python/tvm/relax/frontend/torch/fx_translator.py", line 1421, in from_fx
return TorchFXImporter().from_fx(
File "/srv/workspace/framework/tvm/python/tvm/relax/frontend/torch/fx_translator.py", line 1308, in from_fx
self.env[node] = self.convert_map[func_name](node)
File "/srv/workspace/framework/tvm/python/tvm/relax/frontend/torch/fx_translator.py", line 180, in _add
return lhs + rhs
File "/srv/workspace/framework/tvm/python/tvm/relax/expr.py", line 155, in __add__
return _binary_op_helper(self, other, _op_ffi_api.add) # type: ignore
File "/srv/workspace/framework/tvm/python/tvm/relax/expr.py", line 104, in _binary_op_helper
raise TypeError(f"Please convert {rhs} with `const` first")
TypeError: Please convert 1 with `const` first
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the model-loading failure and start with tvm/relax/frontend/torch/fx_translator.py at _add, then trace the operation into tvm/relax/expr.py. Check whether the failing conversion can be handled for this PyTorch graph; done means the model loads without the reported TypeError.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- compilers, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100