Open
Conversation
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/93fb6115-fced-4b86-8f92-1e7086fb1669 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/0f07273c-6c12-4ab8-8cf9-3a706d15f1ea Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
…ynamicQuantization pass Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/73dad5b1-ff7e-449c-b55c-00d070a88d59 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/73dad5b1-ff7e-449c-b55c-00d070a88d59 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
…c quantization output) Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/e85b5f33-587c-4313-b97e-951b5ee5e35a Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Copilot created this pull request from a session on behalf of
kunal-vaishnavi
May 6, 2026 18:23
View session
…-large-v3-turbo Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/f59cbe21-d819-4b4e-b3b5-85c7218e4fb5 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/d767f7a9-ce1b-4f18-acb0-012134b6a1e6 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
… (36 total) Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/00275554-1df2-42e5-b52d-52c634ef94c8 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/c03b66e2-2af8-43e8-85d8-f3da8631dad4 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/c03b66e2-2af8-43e8-85d8-f3da8631dad4 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/38ce80db-c13b-4147-a3af-0daf773dd491 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/089e82c6-1bd3-479f-94f0-a2ed8d62edb0 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Agent-Logs-Url: https://github.com/microsoft/olive-recipes/sessions/f3040593-bcd7-40b4-854e-1655f3754e97 Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Copilot stopped work on behalf of
kunal-vaishnavi due to an error
May 7, 2026 22:24
Copilot stopped work on behalf of
kunal-vaishnavi due to an error
May 7, 2026 22:28
kunal-vaishnavi
changed the title
Copilot stopped work on behalf of
kunal-vaishnavi due to an error
May 7, 2026 23:03
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
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.
This pull request adds CPU, CUDA, and WebGPU optimization recipes for the OpenAI Whisper models using Olive, enabling efficient INT8 quantization across multiple execution providers. Each backend (CPU, CUDA, WebGPU) gets its own configuration, documentation, and dependency files, making it easier to optimize and deploy the model on different hardware targets.
New optimization recipes and configuration:
whisper-base.en_cpu_int8.json), CUDA (ex:whisper-base.en_cuda_int8.json), and WebGPU (ex:whisper-base.en_webgpu_int8.json) backends, each specifying the appropriate execution provider and quantization pipeline.Documentation and metadata:
cpu/README.md,cuda/README.md,webgpu/README.md) with setup instructions and backend-specific notes.info.ymlfiles for each backend, describing the recipe, device, and execution provider.Dependencies and licensing:
requirements.txtfor each backend, listingolive-aiandonnxruntime-genaias dependencies.Requires: