New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add a typed mode operator. #386
Conversation
Here's the pytorch docs for |
Thx! CUDA's test is here. |
@junjihashimoto Thanks for the pointer. So you're suggesting that I add a CUDA-enabled test for |
Yes, I have native GPU. |
Or we can do a test after merging. |
Is there a good way? The test of gpu is ideally done on ci. |
39e55d2
to
a48dfa8
Compare
LGTM, more testing esp on gpu is always helpful but I also think it's relatively low risk having the same form as median / mean. |
Yeah, the risk is low. Do you want to merge? I think we can add another PR for hspec. |
Hi all, there are some minor issues with this, but we can merge as is. |
@tscholak @junjihashimoto Sorry, I should have replied here earlier, but I was working on writing the hspec tests locally, but I didn't yet have anything I felt comfortable pushing. When @tscholak opens a PR for the hspec tests, I'll try to take a look and figure out what I could have done differently in this PR. |
Hi @cdepillabout, no problem! We are very glad you made this contribution, thanks a lot! |
This PR adds a typed
mode
operator, as per #233.I just talked to @tscholak, and he suggested that I should check that this operator actually works on CUDA. I don't have an nvidia GPU, so I haven't done this, but I would appreciate if someone could check this for me.
Also, because I added the doctests, I didn't add any hspec tests, but I could do this if necessary.
(Note that this PR is based on the current
master
, which does not yet contain a fix for actually running the doctests in CI, but I did check that the doctests I added here run correctly locally.)