-
Notifications
You must be signed in to change notification settings - Fork 74k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[XLA:GPU] Let TritonFusion depend on CUDA or ROCm headers (transitive…
…ly). So far, we guard the dep with `#if GOOGLE_CUDA || TENSORFLOW_USE_ROCM` and return an unimplemented error otherwise. However, having `"triton"` in the build graph makes no sense if neither CUDA nor ROCm toolkits are available at build time. This PR moves the `if_gpu_is_configured` branching upwards in the build graph to `"ir_emitter_unnested`". PiperOrigin-RevId: 636875057
- Loading branch information
1 parent
e6538d9
commit 4549f45
Showing
3 changed files
with
2 additions
and
12 deletions.
There are no files selected for viewing
This file contains 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
This file contains 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
This file contains 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