文件最后提交记录最后更新时间
[feature] inductor_npu_ext: stride/shape check for fused kernel tools Co-authored-by: yurongkun<yurongkun@huawei.com> # message auto-generated for no-merge-commit merge: !2945 merge inductor_check_0421 into master [feature] inductor_npu_ext: stride/shape check for fused kernel tools Created-by: yurongkun Commit-by: yurongkun Merged-by: ascend-robot Description: stride/shape check for fused kernel tools: indcutor_npu_ext新增融合kernel校验工具。不同于inductor原生assert_size功能,本功能主要针对融合kernel 实现功能如下: 1)新增TORCHINDUCTOR_NPU_EXT_LAYOUT_CHECK用于决定是否直接error报错,默认为关 2)打开原生TORCH_COMPILE_DEBUG或者TORCHINDUCTOR_NPU_EXT_LAYOUT_CHECK会生成对比代码.TORCH_COMPILE_DEBUG=1时仅打印日志warning级别 3)shape dim<=1不会校验stride信息,其他场景正常校验 4)针对SymInt/sympy.Expr/int三种场景的输入信息,做对应适配。_safe_int_convert 5)在output.py文件中新增maybe_check_fused_input_layout的codegen代码并在kernel call之前执行 6)新增UT 验证动态和静态图场景是否符合预期 See merge request: Ascend/torchair!294515 天前
[feature] inductor support task queue Co-authored-by: yurongkun<yurongkun@huawei.com> # message auto-generated for no-merge-commit merge: !3064 merge task_queue_up into master [feature] inductor support task queue Created-by: yurongkun Commit-by: yurongkun Merged-by: ascend-robot Description: inductor support task queue See merge request: Ascend/torchair!30649 天前
add uttest for host debugging Co-authored-by: medivh<xuepeng4@huawei.com> # message auto-generated for no-merge-commit merge: !2715 merge tx into master add uttest for host debugging Created-by: medivh-x Commit-by: medivh Merged-by: ascend-robot Description: add uttest for host debugging See merge request: Ascend/torchair!27152 个月前
detect soc by version Co-authored-by: medivh<xuepeng4@huawei.com> # message auto-generated for no-merge-commit merge: !3112 merge master into master detect soc by version Created-by: medivh-x Commit-by: medivh Merged-by: ascend-robot Description: detect soc by version See merge request: Ascend/torchair!311216 小时前