Yorick
Yorick
@asingh9530 the test 'https://github.com/replicate/cog/blob/main/test-integration/test_integration/test_build.py#L9' fails because it tests for a specific error message, which has been changed in this PR. Please update the test to match the new error message.
It looks like the tests test the contents of the dockerfile. Please update these as well.
I think Cog doesn't know which cuda to use because it doesn't see torch directly. Try adding an explicit dependency on torch==2.0.1 in python_packages. (maybe 2.1.0?)
Cog 0.8.6 doesn't support `torch==2.1.2`, try `torch==2.0.1`. (is there a warning about this? there should be) It's weird that this image still works locally, though.
Is it working now?
cc @technillogue working on async
@happy-machine This step tries to import your predict.py, but doesn't run any setup or prediction functions. Are you doing anything time-consuming in predict.py? @rdcoder33 @Sanawar21 currently, cog doesn't support pydantic>=2.0.0....
Quick workaround: add this to your predict.py: ```python import mimetypes mimetypes.add_type("application/octet-stream", ".glb") ``` See also: #1353
Which cog version are you using? You may have more luck with one of the 0.9 beta's, which support list and union inputs.
That's weird. Looks like something installed wrongly. The official instructions are as follows: ``` sudo curl -o /usr/local/bin/cog -L "https://github.com/replicate/cog/releases/latest/download/cog_$(uname -s)_$(uname -m)" sudo chmod +x /usr/local/bin/cog ``` Alternatively, try `sudo...