fix: stabilize A5 validation samples#642
Draft
HecreReed wants to merge 1 commit intohw-native-sys:mainfrom
Draft
fix: stabilize A5 validation samples#642HecreReed wants to merge 1 commit intohw-native-sys:mainfrom
HecreReed wants to merge 1 commit intohw-native-sys:mainfrom
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds support for MSCATTER and MGATHER operations in the NPU validation framework, including logic for index generation and result comparison. It also updates quantization samples to utilize per-row scaling and offsets, simplifying the golden reference generation. Furthermore, the remote validation script now includes a check for required ISA symbols to skip unsupported test cases. Feedback was provided regarding the heuristic used to identify scatter indices, noting an inconsistency with existing logic that could lead to incorrect operand identification.
Comment on lines
+1886
to
+1892
| for p in reversed(init_ptrs): | ||
| p_dtype = _np_dtype_for_cpp(p["cpp_type"]) | ||
| if p.get("role") == "input" and ( | ||
| p_dtype.startswith("np.int") or p_dtype.startswith("np.uint") | ||
| ): | ||
| mscatter_indices_input = p | ||
| break |
There was a problem hiding this comment.
The heuristic for identifying mscatter_indices_input uses reversed(init_ptrs), which selects the last integer input as the indices. This is inconsistent with the tscatter logic (which selects the first integer input) and may be incorrect depending on the operand order of the MSCATTER operation. In mscatter.py, arg0 appears to be the indices and arg1 the data; if so, this heuristic will misidentify arg1 as the indices, potentially breaking the compare_bin_at_indices logic later. Consider if init_ptrs (picking the first) would be more appropriate or if a more robust identification method is needed.
Collaborator
Author
|
/run a5 abs quant quant_asym mgather mscatter partarg |
|
已接收
页面会自动刷新，可以直接看当前阶段、排队情况和最近结果。 |
Codex Review该评论由 review 机器人自动更新。
SummaryReview failed at stage Findings未生成结构化 findings，因为 review 过程提前失败。 Log Tail |
A5 板测失败
失败用例
|
A5 板测失败详情：PR #642mscatter
|
Collaborator
Author
|
/run a5 abs quant quant_asym mgather mscatter partarg |
|
已接收
页面会自动刷新，可以直接看当前阶段、排队情况和最近结果。 |
A5 板测失败
失败用例
|
A5 板测失败详情：PR #642mscatter
|
Collaborator
Author
|
/run a5 abs quant quant_asym mgather mscatter partarg |
|
已接收
页面会自动刷新，可以直接看当前阶段、排队情况和最近结果。 |
A5 板测失败
失败用例
|
A5 板测失败详情：PR #642quant
quant_asym
mscatter
mgather
abs
|
Collaborator
Author
|
/run a5 abs quant quant_asym mgather mscatter partarg |
|
已接收
页面会自动刷新，可以直接看当前阶段、排队情况和最近结果。 |
A5 板测失败
失败用例
|
A5 板测失败详情：PR #642mscatter
|
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.
Summary
Validation