Preview / Blocked by upstream: MLX on three clouds: Fal, Modal, Replicate#256
Draft
anthonywu wants to merge 7 commits intofilipstrand:mainfrom
Draft
Preview / Blocked by upstream: MLX on three clouds: Fal, Modal, Replicate#256anthonywu wants to merge 7 commits intofilipstrand:mainfrom
anthonywu wants to merge 7 commits intofilipstrand:mainfrom
Conversation
anthonywu
changed the title
filipstrand
reviewed
Aug 26, 2025
pyproject.toml
Outdated
| "huggingface-hub>=0.24.5,<1.0", | ||
| "matplotlib>=3.9.2,<4.0", | ||
| "mlx>=0.27.0,<0.28.0", | ||
| "mlx>=0.27.0,<0.29.0", |
Owner
There was a problem hiding this comment.
Tested this locally too and works fine!
anthonywu
force-pushed
the
mlx-on-clouds
branch
from
a58bb08 to
f775752
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Update: Jan 31, 2026
All three cloud GPU service examples have been updated with the release from #321
modal run: nvproxy: Add support for UVM_ENABLE_READ_DUPLICATION and UVM_SET_ACCESSED_BY. google/gvisor#12436 unblocks the issue at the upstreamgvisorproject, but that runtime update has not been adopted by Modal yet (same error as August attempt)fal run fal_run_mflux.pywill start a remote app, and even a playground GUI, the generation apparently works if you observe only the log text content – tqdm progress bars complete, but the Result does not return to the playground GUI. Will investigate whether this is just my skill issue with Fal Apps.cog predict- TBDUpdate: Aug 23, 2025
This is WIP to try out mflux on Linux (CPU for now) on Fal, Replicate Cog and Modal
When I get these to work, we can merge these as
tools/*resources that isn't part of the official project but can be copy/pasteable to deployable application layers.