Add FP16 support for Whisper model #15427
Merged
Conversation
This file contains hidden or 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
Contributor
|
Add a test case with hf-internal-testing/tiny-random-WhisperForConditionalGeneration model? |
Contributor
Author
|
ContribOperators.md also needs to be updated since FP16 is added in contrib_defs.cc . Is there a specific command to run gen_contrib_doc.py? |
Contributor
You can download ContribOperators.md from kernelDocumentation build pipeline (see the failed pipeline job) published artifacts: https://dev.azure.com/onnxruntime/onnxruntime/_build/results?buildId=952726&view=artifacts&pathAsName=false&type=publishedArtifacts |
Member
Windows GPU CI pipeline generates and unloads them as artifacts. You can download the updated version there: |
Contributor
Author
Sure. We may merge this PR first so people can run Wisper FP16 model. The HF testing model will be added in a separate PR. |
yufenglee
approved these changes
Apr 9, 2023
tianleiwu
approved these changes
Apr 9, 2023
smk2007
pushed a commit
that referenced
this pull request
Apr 14, 2023
Current ORT can only run inference for Whisper FP32 model. This PR adds FP16 support.
hanbitmyths
pushed a commit
that referenced
this pull request
Apr 19, 2023
### Description This PR contains fusion-level and kernel-level optimizations for [OpenAI's Whisper](https://github.com/openai/whisper). Some of the added optimizations include: - Pruning of duplicate/unnecessary inputs and outputs - Fusion support for Whisper models with or without these inputs/outputs (e.g. with these inputs/outputs if exporting with an older official Optimum version, without these inputs/outputs if exporting with Optimum from source) - Attention fusions - For Whisper's encoder and decoder - Modified symbolic shape inference for present output when no past input exists (for decoder) - Multi-head attention fusions - For Whisper's decoder and decoder with past - Packed MatMul for the 3 MatMuls excluded in multi-head attention fusion - Attention kernel changes - CPU: - Different Q and KV sequence lengths - Parallel memset for large sequence lengths - Convert broadcast add after MatMul of Q and K (add_qk) to element-wise add - Separate present key-value output into present key and present value (for multi-head attention spec) - CUDA: - Use memory efficient attention compute kernel with present state (for decoder) - Multi-head attention kernel changes - CPU: - Introduction of multi-head attention CPU kernel (previously did not exist) - Use AddBiasReshape instead of AddBiasTranspose when sequence length = 1 (for decoder with past) - Different Q, K, V input shapes - Pass past key and past value directly as key and value - CUDA: - Use memory efficient attention compute kernel with past and/or present state (for decoder with past) ### Usage To use the optimizations, run the ORT transformer optimizer script as follows: ``` $ cd onnxruntime/onnxruntime/python/tools/transformers/ $ python3 optimizer.py --input <filename>.onnx --output <filename>.onnx --model_type bart --num_heads <number of attention heads, depends on the size of the whisper model used> --hidden_size <attention hidden size, depends on the size of the whisper model used> --use_external_data_format --use_multi_head_attention ``` Once optimized, here's an example of how to run Whisper with [Hugging Face's Optimum](https://github.com/huggingface/optimum): ``` from transformers.onnx.utils import get_preprocessor from optimum.onnxruntime import ORTModelForSpeechSeq2Seq from optimum.pipelines import pipeline as ort_pipeline import whisper # Installed from OpenAI's repo - setup instructions at https://github.com/openai/whisper/ directory = './whisper_opt' # Where the optimized ONNX models are located model_name = 'openai/whisper-tiny' device = 'cpu' # Get pipeline processor = get_preprocessor(model_name) model = ORTModelForSpeechSeq2Seq.from_pretrained( directory, use_io_binding=(device == 'cuda'), provider='CPUExecutionProvider', ).to(device) pipe = ort_pipeline( "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, device=(-1 if device == 'cpu' else 0), ) # Load audio file and run pipeline audio = whisper.load_audio('tests/jfk.flac') audio = whisper.pad_or_trim(audio) outputs = pipe([audio]) print(outputs) ``` Note: In order to use these changes with Optimum, it is recommended to use Optimum from source to have the following changes: - huggingface/optimum#872 - huggingface/optimum#920 ### Motivation and Context This PR helps the following issues: - #15100 - #15235 - huggingface/optimum#869 (work in progress) This PR can be used with the other currently merged Whisper PRs: - #15247 - #15339 - #15362 - #15365 - #15427 This PR uses changes from the following merged PRs: - #14198 - #14146 - #14201 - #14928 (this introduced the new multi-head attention spec)
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.
Current ORT can only run inference for Whisper FP32 model. This PR adds FP16 support.