Pull Request已成功合入, 合并人@ascend-robot
(感谢 luqichao 的贡献)变更摘要
本 PR 为同步 PR,将 TA3.6 编译模式适配同步至 master(来源 PR !45315,关联 Issue #4364)。核心改动是:将 NPUKernelType.SIMT_TEMPLATE 对应的 compile_mode 由 unstructured_in_simt 调整为 simd_simt_template,并在 torch_npu/_inductor/runtime/triton_heuristics.py 的 TTIR 构建与 Triton 预编译路径中,对缺失或为 None 的 compile_mode 统一回退到该有效编译模式,确保调用 triton.compile 时始终传入合法的编译模式。
主要改动
- 调整 SIMT 编译模式取值:在
torch_npu/_inductor/codegen/triton_utils.py的NPUKernelType.compile_mode()中,将SIMT_TEMPLATE的返回值由"unstructured_in_simt"改为"simd_simt_template",以适配 TA3.6 的编译模式。 - TTIR 构建路径的编译模式兜底:在
torch_npu/_inductor/runtime/triton_heuristics.py的NPUCachingAutotuner第一处compile_meta['compile_mode']赋值处,使用cfg_kwargs.get('compile_mode') or NPUKernelType.SIMT_TEMPLATE.compile_mode(),当配置缺失或为None时回退到simd_simt_template。 - Triton 预编译路径的编译模式兜底:在
torch_npu/_inductor/runtime/triton_heuristics.py的NPUCachingAutotuner第二处compile_meta['compile_mode']赋值处,采用相同的or回退逻辑,保证预编译阶段同样传入有效的编译模式。


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.
You can self-configure the PR merge rules for this repository. For more details, please refer to Here.
PR Approval Progress
✅ Congratulations! All modules have met the lgtm and approve requirements.
Module Approval Details
| module | lgtm status | approve status |
|---|---|---|
| torch_npu/_inductor | ✅ weizhan4, rain-666 (2/2) | ✅ weizhan4 (1/1) |
💡 Tip:
- Committer can comment
/approveor/lgtm- Commenting
/approveimplies both code review (lgtm) and intent to merge (approve)
CLA Signature Pass
luqichao, thanks for your pull request. All authors of the commits have signed the CLA. 👍


当前仓库存在以下 保护分支 :
| Protected Branch | Version | Release |
|---|---|---|
| master | ||
| v2.7.1 | ||
| v2.10.0 | ||
| v2.11.0 | ||
| v2.9.0 | ||
| v2.12.0 | ||
| v2.11.0-26.1.0 | ||
| v2.12.0-26.1.0 | ||
| v2.10.0-26.1.0 | ||
| v2.9.0-26.1.0 | ||
| v2.7.1-26.1.0 | ||
| ci-test |
评论 /sync <branch1> <branch2> ... 可将当前 PR 修改同步到其它分支(创建同步 PR):
a) 如果当前 PR 是 Open 状态,同步操作将延迟到 PR 被合并时执行
b) 如果当前 PR 已经 Merged,将立即执行同步操作
注意:
- /sync 命令可以指定同步到多个分支,仅最后一个 /sync 命令生效
- 如果创建的同步 PR 不正确,可通过向同步 PR 的源分支提交轻量级 PR 完善,或使用 /close 命令关闭


ascend docs pipeline is running...


✅ 跳过 docs ci 检查,没有需要检查的文档文件


| 阶段 | 任务名 | 状态 | 详情 |
|---|---|---|---|
| 编译构建 | Build_X86 | ✅ | >>> |
| Build_ARM | ✅ | >>> | |
| Build_X86_torchair | 🛑 | >>> | |
| Build_ARM_torchair | 🛑 | >>> | |
| patch_test | 🛑 | >>> | |
| Build_X86_213 | ✅ | >>> | |
| Build_ARM_213 | ✅ | >>> | |
| 恶意代码检查 | Antipoison | ✅ | >>> |
| 编码安全与规范检查 | codecheck_pre-commit | ✅ | >>> |
| check_error | ✅ | >>> | |
| lintrunner | ✅ | >>> | |
| 开源片段检查 | SCA | ✅ | >>> |
| 开发者测试 | UT_ARM_A3_Part_01 | 🛑 | >>> |
| UT_ARM_A3_Part_02 | 🛑 | >>> | |
| UT_ARM_A2_Part_01 | ✅ | >>> | |
| UT_ARM_A2_Part_02 | ✅ | >>> | |
| UT_ARM_A2_Part_03 | ✅ | >>> | |
| UT_inductor_Part_01 | 🛑 | >>> | |
| UT_inductor_Part_02 | 🛑 | >>> | |
| UT_inductor_Part_03 | 🛑 | >>> | |
| UT_inductor_Part_04 | 🛑 | >>> | |
| UT_DIST_ARM_Part_01 | 🛑 | >>> | |
| UT_DIST_ARM_Part_02 | 🛑 | >>> | |
| UT_DIST_ARM_Part_03 | 🛑 | >>> | |
| UT_DIST_ARM_Part_04 | 🛑 | >>> | |
| UT_ARM_A2_Select_Part_01 | ✅ | >>> | |
| UT_ARM_A2_Select_Part_02 | ✅ | >>> | |
| UT_ARM_A2_Part_01_213 | ✅ | >>> | |
| UT_ARM_A2_Part_02_213 | ✅ | >>> | |
| UT_ARM_A2_Part_03_213 | ✅ | >>> | |
| UT_inductor_Part_01_213 | 🛑 | >>> | |
| UT_inductor_Part_02_213 | 🛑 | >>> | |
| UT_inductor_Part_03_213 | 🛑 | >>> | |
| UT_inductor_Part_04_213 | 🛑 | >>> | |
| UT_DIST_ARM_Part_01_213 | 🛑 | >>> | |
| UT_DIST_ARM_Part_02_213 | 🛑 | >>> | |
| UT_DIST_ARM_Part_03_213 | 🛑 | >>> | |
| UT_DIST_ARM_Part_04_213 | 🛑 | >>> | |
| UT_ARM_A2_Select_Part_01_213 | ✅ | >>> | |
| UT_ARM_A2_Select_Part_02_213 | ✅ | >>> | |
| 流水线 | PR-pipeline_pytorch | ✅ | >>> |
- compile、compile_inductor、compile_torchair : 运行流水线
- retry : 重试流水线所有失败子任务
- retry <任务名> : 仅重试指定失败子任务
- stop : 停止流水线


/lgtm




同步说明
401a9c714b191bf8e42a52ca8e61088f468cbe6dmasterNPUKernelType.SIMT_TEMPLATE对应的compile_mode从unstructured_in_simt修改为simd_simt_template,同步 TA3.6 编译模式适配。None的compile_mode统一使用simd_simt_template,确保调用triton.compile时始终传入有效的编译模式。