11d3ce9edb
Revert "chore(deps): Bump torchvision from 0.18.1+rocm6.0 to 0.20.0+cu118 in /backend/python/diffusers" ( #4008 )
...
Revert "chore(deps): Bump torchvision from 0.18.1+rocm6.0 to 0.20.0+cu118 in …"
This reverts commit 14cb620cd8
2024-10-29 09:25:17 +01:00
14cb620cd8
chore(deps): Bump torchvision from 0.18.1+rocm6.0 to 0.20.0+cu118 in /backend/python/diffusers ( #3997 )
...
chore(deps): Bump torchvision in /backend/python/diffusers
Bumps torchvision from 0.18.1+rocm6.0 to 0.20.0+cu118.
---
updated-dependencies:
- dependency-name: torchvision
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-28 23:33:35 +00:00
74eaf02484
feat(diffusers): support flux models ( #3129 )
...
* feat(diffusers): support flux models
This adds support for FLUX models. For instance:
https://huggingface.co/black-forest-labs/FLUX.1-dev
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
* feat(diffusers): support FluxTransformer2DModel
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
* Small fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
2024-08-11 01:31:53 +02:00
0c0bc18c94
fix(diffusers): pin torch and torchvision ( #1592 )
...
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
2024-08-10 10:10:47 +02:00
2e2a0dffbc
fix(diffusers-hipblas): pin to rocm6.1
...
As per https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-08-09 22:36:10 +02:00
a507c13f8e
fix(diffusers): do not specify --pre as with pip
...
drop --pre as it is not supported by `uv`
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-08-08 22:21:05 +02:00
8317839ca5
fix(diffusers): use nightly rocm for hipblas builds ( #3202 )
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-08-08 17:28:07 +02:00
61b5602111
fix(python): move accelerate and GPU-specific libs to build-type ( #3194 )
...
Some of the dependencies in `requirements.txt`, even if generic, pulls
down the line CUDA libraries.
This changes moves mostly all GPU-specific libs to the build-type, and
tries a safer approach. In `requirements.txt` now are listed only
"first-level" dependencies, for instance, grpc, but libs-dependencies
are moved down to the respective build-type `requirements.txt` to avoid
any mixin.
This should fix #2737 and #1592 .
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
2024-08-07 17:02:32 +02:00
16433d2e8e
fix: install pytorch from proper index for hipblas builds ( #2413 )
...
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com >
2024-05-26 18:05:52 +00:00
