Google Colab: KeyError Primitive function cuda_i64_to_f16 has already registered #444
Labels
bug
Something isn't working
Comments
vadiklyutiy
pushed a commit
that referenced
this issue
Dec 19, 2024
…le compiling the model `sam` (#444) Closes #325 The error in the linked issue was caused by [this code segment](https://github.com/CentML/hidet/blob/bfbb4db6d7792ed3de3be4e9702e597b8fbbe373/python/hidet/graph/transforms/conv_channel_last.py#L46-L75) in `graph/transforms/conv_channel_last.py`. By the logic flow of this code segment, if the operator `node` has two inputs, the first one with rank 4 and the second rank 3(an example case in the model: an `AddOp` where the first input has shape `[1, 256, 64, 64]` and the second `[256, 1, 1]`) , then by the time the code reaches the line 75, the variable `new_perm`would have value `[1, 2, 0]`, and this value will be recorded as the permutation scheme used to get the new output, which is incorrect as the appropriate value should be `[0, 2, 3, 1]` here.
vadiklyutiy
pushed a commit
that referenced
this issue
Dec 20, 2024
…le compiling the model `sam` (#444) Closes #325 The error in the linked issue was caused by [this code segment](https://github.com/CentML/hidet/blob/bfbb4db6d7792ed3de3be4e9702e597b8fbbe373/python/hidet/graph/transforms/conv_channel_last.py#L46-L75) in `graph/transforms/conv_channel_last.py`. By the logic flow of this code segment, if the operator `node` has two inputs, the first one with rank 4 and the second rank 3(an example case in the model: an `AddOp` where the first input has shape `[1, 256, 64, 64]` and the second `[256, 1, 1]`) , then by the time the code reaches the line 75, the variable `new_perm`would have value `[1, 2, 0]`, and this value will be recorded as the permutation scheme used to get the new output, which is incorrect as the appropriate value should be `[0, 2, 3, 1]` here.
|
Egor, with hidet==0.5.0 Test passed successfully. $ pip show hidet
Name: hidet
Version: 0.5.0
Summary: Hidet: a compilation-based DNN inference framework.
Home-page: https://docs.hidet.org
Author:
Author-email:
License: Apache-2.0
Location: /tmp/venv/lib/python3.10/site-packages
Requires: astunparse, click, cuda-python, filelock, lark, numpy, nvtx, packaging, psutil, pytest, requests, scipy, tabulate, tomlkit, tqdm
Required-by:
$ cat tmp.py
import hidet
print('hidet:', hidet.__version__)
$ python tmp.py
hidet: 0.5.0
If you still has same issue in your env please feel free to reopen. |
vadiklyutiy
pushed a commit
that referenced
this issue
Dec 26, 2024
…le compiling the model `sam` (#444) Closes #325 The error in the linked issue was caused by [this code segment](https://github.com/CentML/hidet/blob/bfbb4db6d7792ed3de3be4e9702e597b8fbbe373/python/hidet/graph/transforms/conv_channel_last.py#L46-L75) in `graph/transforms/conv_channel_last.py`. By the logic flow of this code segment, if the operator `node` has two inputs, the first one with rank 4 and the second rank 3(an example case in the model: an `AddOp` where the first input has shape `[1, 256, 64, 64]` and the second `[256, 1, 1]`) , then by the time the code reaches the line 75, the variable `new_perm`would have value `[1, 2, 0]`, and this value will be recorded as the permutation scheme used to get the new output, which is incorrect as the appropriate value should be `[0, 2, 3, 1]` here.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
I am trying to install hidet 0.3.1 on Google Colab
To Reproduce
Expected behavior
To see the hidet version
Additional context
Instead of the hidet version I am getting this error:
The text was updated successfully, but these errors were encountered: