变更摘要

本 PR 修复 NpuWeightQuantizedLinear.forward 在输入为非连续张量时调用 npu_weight_quant_batchmatmul 触发 aclnn EZ1001 报错的问题。inputs.reshape(-1, K) 的结果仅在输入张量本身连续时才连续，当输入来自 K 维切片（如 QKV 联合投影拆分出的 hidden_states）等非连续布局时，传给算子的 2D 张量 is_contiguous() == False，从而抛出 EZ1001: only support x tensor is contiguous or transpose last two dims。修复方案是在 reshape 后显式调用 .contiguous()，对已连续张量该方法零拷贝返回原 view，不影响常规路径性能，并同步新增 CPU 环境 mock torch_npu 的单元测试守护该回归场景。

主要改动

• 修复 NpuWeightQuantizedLinear.forward 输入连续性: 在 amct_pytorch/classic/deploy_op/weight_npu_quant_module.py 中将 inputs.reshape(-1, inputs.shape[-1]) 改为 inputs.reshape(-1, inputs.shape[-1]).contiguous()，确保传给 npu_weight_quant_batchmatmul 的 2D 张量连续，消除非连续输入触发的 EZ1001 报错。
• 新增单元测试文件: 添加 tests/unit_test/classic/test_weight_npu_quant_module.py，通过 _install_fake_torch_npu 注册 mock 的 torch_npu 模块并记录传入 npu_weight_quant_batchmatmul 的 x，在 CPU 环境验证算子输入张量的连续性。
• 测试用例覆盖核心行为: test_forward_input_to_op_is_contiguous 用 K 维切片 3D 输入断言传入算子的张量连续（移除修复后该用例失败）；test_forward_output_shape_restored 验证输出形状能正确恢复为原始前导维度形状。

代码审查

✅ 未发现问题

Hi @niwang66, welcome to submitting your first PR to amct!

PR Merge Steps

1. CLA Signing

If the current PR label includes cann-cla/yes, it means you have signed the CLA and can proceed to the next step. If the label includes cann-cla/no, please sign the CLA first. If you have any questions, please refer to the FAQ.

2. CI Check

Please comment /compile to trigger the CI pipeline check. If the CI run is successful, the PR will be tagged with ci-pipeline-passed and you can proceed to the next step. If the CI run fails, the PR will be tagged with ci-pipeline-failed, please check the CI logs to fix the issues in the PR. If you have any questions, please refer to the FAQ.

3. Code Review

After CI passes, please refer to the PR Approval Progress and proactively @ the committers in the table to review the code. After approval, committers will comment /lgtm and /approve. Once the lgtm and approved labels are successfully added, the PR will be merged automatically.

Thanks for your pull-request.
The full list of commands accepted by me can be found at here.
You can get sig-info at here.
For more, you also can visit HICANN.

PR Approval Progress

⚠️ This PR does not yet meet the following requirements:lgtm (requires ≥ 2 person(s) per module)、approve (requires ≥ 1 person(s) per module)

Module Approval Details

💡 Tip:

• Committer can comment /approve or /lgtm
• Commenting /approve implies both code review (lgtm) and intent to merge (approve)

CLA Signature Guide

@niwang66 , thanks for your pull request.

The following commit(s) have not signed Contributor License Agreement (CLA).

If you need to sign CLA, you can click here to sign the CLA.

If you need to check if the email is set up correctly, you can click here to do it in the FAQs.

After signing the CLA or updating the email, you must comment /check-cla to check the CLA status again.