support model_type == "inkling_mm_model" - #2214
Open
xin3he wants to merge 10 commits into
Open
Conversation
Signed-off-by: Xin He <xin3.he@intel.com>
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
…ation Signed-off-by: Xin He <xin3.he@intel.com>
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
… tensor handling Signed-off-by: Xin He <xin3.he@intel.com>
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
for more information, see https://pre-commit.ci
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
…paths and generic projection names Signed-off-by: Xin He <xin3.he@intel.com>
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Contributor
Author
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
Collaborator
|
/azp run Unit-Test-CUDA-AutoRound |
|
Azure Pipelines successfully started running 1 pipeline(s). |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This pull request introduces improved support for handling fused 3-D Mixture-of-Experts (MoE) expert weights, especially for architectures whose inference engines require these weights to remain fused (such as
inkling_mm_model). The main changes ensure that such fused tensors are preserved and quantized appropriately, rather than being split into per-expert 2-D tensors.Fused MoE expert weight support:
_KEEP_FUSED_EXPERT_MODEL_TYPESinmissing_tensors.pyto identify model types that require fused expert tensors to be preserved, and updatedsplit_fused_expert_tensorsto skip splitting for these types. [1] [2] [3] [4]_is_moe_fused_expert_weightand_quantize_moe_fused_expert_weightinmodel_free_utils.pyto detect and quantize fused 3-D expert weights in place using MXFP quantization, preserving the fused layout._quantize_single_tensorto use the new quantization logic for fused MoE weights._process_shardto correctly track and process fused 3-D MoE expert weights, ensuring they are not mistakenly excluded from quantization.These changes improve compatibility with architectures that require fused expert weights, prevent errors during quantization, and ensure correct handling for advanced MoE models.
Type of Change
New feature
Related Issues
Fixes or relates to #
Checklist Before Submitting
/azp run Unit-Test-CUDA-AutoRound.