Bump protobuf from 4.25.8 to 5.29.6 in /onnxruntime/python/tools/transformers/models/llama #933
+158
−14
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
### Description Refer to V1 of the fix here: microsoft#27214 This PR includes all fixes from the V1 PR + logic to invalidate the lhs cache pointers in case the pad buffer's underlying buffer has changed due to a resize. The ARM team will look at potentially enhancing this logic after the 1.24.0 release. ### Motivation and Context Fix microsoft#26669
### Description According to https://github.com/microsoft/onnxruntime/blob/main/docs/ContribOperators.md#commicrosoftmoe, > swiglu_limit : float The limit used to clamp in SwiGLU. No clamp when limit is not provided. However, currently, the default is set to 0, meaning we clamp to 0 if no limit is provided. ### Motivation and Context Fixes microsoft#27220. See there for bug description and reproduction. Hoping to get this in before 1.24.0 releases. cc @guschmue
### Description Fixed for fallback provider logic bug when creating inference session can lead to losing GPU acceleration ### Motivation and Context Fixing this for the PR here [microsoft#25145](microsoft#25145)
…soft#27217) This pull request updates the attention kernel selection logic and clarifies support for unidirectional (causal) attention in the CUDA attention implementation. The main changes focus on improving documentation, removing outdated comments, and explicitly setting the kernel type for better maintainability and clarity. Kernel selection and configuration improvements: * Explicitly set the `kernel_type` field to `AttentionKernel_Unfused` in the `AttentionData` structure to clarify which kernel is being used and improve future extensibility. Documentation and code clarity: * Added comments to clarify that unidirectional (causal) attention is supported by several attention kernel implementations, and that the TRT fused runner is only used for non-unidirectional cases, as enforced elsewhere. * Removed outdated TODO comments regarding parameter continuation and kernel selection, as these are now handled more explicitly in the code. [[1]](diffhunk://#diff-0701e4cc6d4951894ae1a60f35c1e6c0f69ba7595f896a23c8f5ed7265eab4ffL194) [[2]](diffhunk://#diff-0701e4cc6d4951894ae1a60f35c1e6c0f69ba7595f896a23c8f5ed7265eab4ffL223-R227)
… available (microsoft#27206) ### Description As title. Checking if FlashAttention exists check includes if torch has CUDA support, the system has the right device to run FlashAttention, etc. ### Motivation and Context Fix Windows CUDA CI failures --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
) ### Description Takeaway from microsoft#26144 Resolve microsoft#26144 ### Motivation and Context Improve kernel input validation for ConvTranspose --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: Edward Chen <18449977+edgchen1@users.noreply.github.com>
Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 4.25.8 to 5.29.6. - [Release notes](https://github.com/protocolbuffers/protobuf/releases) - [Commits](https://github.com/protocolbuffers/protobuf/commits) --- updated-dependencies: - dependency-name: protobuf dependency-version: 5.29.6 dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com>
dependabot
bot
added
dependencies
jatinwadhwa921
force-pushed
the
master
branch
from
b9558ca to
711d155
Compare
Author
|
A newer version of protobuf exists, but since this PR has been edited by someone other than Dependabot I haven't updated it. You'll get a PR for the updated version as normal once this PR is merged. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Bumps protobuf from 4.25.8 to 5.29.6.
Release notes
Sourced from protobuf's releases.
... (truncated)
Commits
Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting
@dependabot rebase.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
@dependabot rebasewill rebase this PR@dependabot recreatewill recreate this PR, overwriting any edits that have been made to it@dependabot show <dependency name> ignore conditionswill show all of the ignore conditions of the specified dependency@dependabot ignore this major versionwill close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this minor versionwill close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this dependencywill close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)You can disable automated security fix PRs for this repo from the Security Alerts page.