Skip to content

Conversation

@anton-l
Copy link
Member

@anton-l anton-l commented Oct 3, 2022

  • Use a local Hub cache instead of NFS
  • Less ONNX pipeline steps, use CPU runtime (needs a custom docker image for CUDA to work)

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Oct 3, 2022

The documentation is not available anymore as the PR was closed or merged.

@anton-l anton-l changed the title [CI] Localize the HF cache [CI] Speed up slow tests Oct 3, 2022
@anton-l anton-l merged commit 1070e1a into main Oct 3, 2022
@patrickvonplaten
Copy link
Contributor

Nice!

@kashif kashif deleted the ci-cache-rework branch October 7, 2022 14:05
prathikr pushed a commit to prathikr/diffusers that referenced this pull request Oct 26, 2022
* [CI] Localize the HF cache

* pip cache

* de-env

* refactor matrix

* fix fast cache

* less onnx steps

* revert

* revert pip cache

* revert pip cache

* remove debugging trigger
PhaneeshB pushed a commit to nod-ai/diffusers that referenced this pull request Mar 1, 2023
…ngface#708)

* [SharkInference] Make SharkInference compile the entire module

-- Previously SharkInference was compiling and providing run APIs
   for a harcoded function with function name "forward".
-- This commit makes the compiling functionality generic and now
   any function being defined within the module can be run.
-- It also creates an API to fetch all the function names defined
   within the compiled module.
-- This commit updates both web and command-line execution of Stable
   Diffusion to use new API of  SharkInference.

Signed-off-by: Abhishek Varma <[email protected]>
yoonseokjin pushed a commit to yoonseokjin/diffusers that referenced this pull request Dec 25, 2023
* [CI] Localize the HF cache

* pip cache

* de-env

* refactor matrix

* fix fast cache

* less onnx steps

* revert

* revert pip cache

* revert pip cache

* remove debugging trigger
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants