fix quant_type=1x128(128x128) can't use tuned_fmoe cfg #758
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
There was a problem hiding this comment.
Pull Request Overview
This PR fixes a naming issue where QuantType.per_128x128 was incorrectly being used instead of QuantType.per_1x128, preventing the use of tuned configurations for this quantization type. The fix ensures consistent naming across the codebase and enables proper configuration lookup.
- Replaces all instances of
per_128x128withper_1x128across multiple files - Updates configuration files to use the correct quantization type name
- Adds conversion logic to handle legacy
per_128x128references
Reviewed Changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| hsa/gfx942/fmoe_2stages/tune.py | Updates quantization type checks and adds conversion logic for legacy references |
| csrc/ck_gemm_moe_2stages_codegen/gen_instances.py | Adds argument conversion from per_128x128 to per_1x128 |
| csrc/ck_gemm_moe_2stages_codegen/gemm_moe_ck2stages_common.py | Updates the supported quantization types list |
| aiter/ops/moe_op.py | Fixes the quantization type conversion logic |
| aiter/fused_moe.py | Updates quantization type references and adds remapping support |
| aiter/configs/untuned_fmoe.csv | Updates configuration entry to use correct quantization type |
| aiter/configs/tuned_fmoe.csv | Updates configuration entry to use correct quantization type |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
valarLip
approved these changes
Aug 5, 2025
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.
No description provided.