Fix for docs on deepspeed inference #482
Open
Conversation
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 patch would do the basic setup (that would still require compilation at first run): josemduarte@0183be7 . |
|
Good catch on the wrong parameter name! CUTLASS should be installed with the You're right though that this step is currently missing from the Docker image, we will update that. |
ljarosch
requested changes
Dec 7, 2024
| @@ -147,7 +147,7 @@ Some commonly used command line flags are here. A full list of flags can be view | |||
|
|
|||
| The **DeepSpeed DS4Sci_EvoformerAttention kernel** is a memory-efficient attention kernel developed as part of a collaboration between OpenFold and the DeepSpeed4Science initiative. | |||
|
|
|||
| If your system supports deepseed, using deepspeed generally leads an inference speedup of 2 - 3x without significant additional memory use. You may specify this option by selecting the `--use_deepspeed_inference` argument. | |||
| If your system supports deepspeed, using deepspeed generally leads an inference speedup of 2 - 3x without significant additional memory use. You may specify this option by selecting the `--use_deepspeed_evoformer_attention` argument. An additional requirement for this option is the [CUTLASS repository](https://github.com/NVIDIA/cutlass). You will need to clone it and set environment variable `CUTLASS_PATH` to point to it, see [instructions](https://www.deepspeed.ai/tutorials/ds4sci_evoformerattention/). | |||
There was a problem hiding this comment.
@josemduarte Would you mind removing the line about CUTLASS given that it should be covered by the standard setup already?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
The main issue is that the parameter name did not coincide with the code.
Question: could the deepspeed extra dependency on CUTLASS be baked into the docker image? I could give it a try but I'm wondering if someone has come across issues with that.