Readme modification #1700
Open
Readme modification #1700
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
yafshar
reviewed
Jan 16, 2025
examples/image-to-text/README.md
Outdated
| @@ -17,55 +17,11 @@ limitations under the License. | |||
| # Image to Text Examples | |||
| This directory contains a script that showcases how to perform image to text generation on Intel® Gaudi® AI Accelerators. | |||
|
|
|||
| ## Single-HPU inference | |||
| Habana FusedSDPA is a fused and optimized implementation of torch.nn.functional.scaled_dot_product_attention() for Gaudi. For more details, refer to [Gaudi online documentation](https://docs.habana.ai/en/latest/PyTorch/Model_Optimization_PyTorch/Optimization_in_PyTorch_Models.html?highlight=fusedsdpa#using-fused-scaled-dot-product-attention-fusedsdpa). We optimized many models with FusedSDPA optimization as in optimum/habana/transformers/models. If models are not optimzied with FusedSDPA, it uses SDPA implementation. | |||
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
yafshar
reviewed
Jan 16, 2025
Comment on lines
30
to
39
| Finetune model can be done as single device, multi-devices with mpi or deepspeed. | ||
|
|
||
| For multi-devices training with mpi, add the following before run_glue.py where X is device number | ||
| > python ../gaudi_spawn.py \ | ||
| > --world_size X --use_mpi run_glue.py \ | ||
|
|
||
| For multi-devices training with deepspeed, add the following before run_glue.py and deepspeed config with --deepspeed after where X is device number | ||
| > python ../gaudi_spawn.py \ | ||
| > --world_size X --use_deepspeed run_glue.py --deepspeed \ | ||
|
|
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
jiminha
reviewed
Jan 16, 2025
vidyasiv
reviewed
Jan 17, 2025
Co-authored-by: Vidya Galli <[email protected]>
Co-authored-by: Vidya Galli <[email protected]>
regisss
reviewed
Jan 20, 2025
examples/image-to-text/README.md
Outdated
| --bf16 \ | ||
| --sdp_on_bf16 | ||
| ``` | ||
| Inference with FP8 precision are enabled using [Intel Neural Compressor (INC)](https://docs.habana.ai/en/latest/PyTorch/Inference_on_PyTorch/Inference_Using_FP8.html), which provides model measurement and quantization capabilities in PyTorch. |
There was a problem hiding this comment.
https://docs.habana.ai/en/latest/PyTorch/Inference_on_PyTorch/Inference_Using_FP8.html returns "page not found"
| ``` | ||
| Inference with FP8 precision are enabled using [Intel Neural Compressor (INC)](https://docs.habana.ai/en/latest/PyTorch/Inference_on_PyTorch/Inference_Using_FP8.html), which provides model measurement and quantization capabilities in PyTorch. | ||
| More information on enabling FP8 in SynapseAI is available here: | ||
| https://docs.habana.ai/en/latest/PyTorch/Inference_on_PyTorch/Inference_Using_FP8.html |
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
Co-authored-by: regisss <[email protected]>
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.
Simplify ReadMe for text-classification, text-feature-extraction, and image-to-text.
What does this PR do?
Fixes # (issue)
Before submitting