- 27 10月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Matmul kernels use primitive * refine * fix Co-authored-by: Nguo ran <360112263@qq.com> Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 26 10月, 2021 2 次提交
-
-
由 Juncheng 提交于
-
由 ZZK 提交于
* dev torch style permute kernel * Refine * fix batch permute launch condition * fix batch permute dispatch logic * remove redundant header file * simplified check logic * use permute primitives in transpose kernels * fix batch permute logic and avoid mod * remove redundant templates * fix grid step * add grid for loop to avoid the elementnum is too large * fix bug when hw is not divided by tile size * refine format * add a copy kernel as a baseline * remove annotation * add copy kernel * add sync * use batch permute for profile * add copy tile baseline * simplify params for copy kernel * add slow copy kernel * use mul to instead mod and remove copy * use movement size = 4 when h w is modify by 2 * Add temp process for half2 * add half2 specialized kernel * remove redundant license * simplified code * fix format * fix comment * fix comment * use bad for loop condition * merge half2 in load * fix bad for loop in batch permute * refine * use align storage * refine * fix comment * fix comment * fix format * add const and remove redundant header file * remove register macro * refine cuda code * fix guoran comment * fix format * fix some details * remove cuda graph * fix for 0d tensor Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 23 10月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Fix SimplifyPermutation * fix * fix typo * fix * add test * fix init Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 22 10月, 2021 1 次提交
-
-
由 guo ran 提交于
* interface primitive::softmax * refine Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 21 10月, 2021 4 次提交
-
-
由 Juncheng 提交于
Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
由 Juncheng 提交于
* Remove primitiveCudaGraphSupport * fix Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
由 Juncheng 提交于
* Apply2 * fix * CastFunctor::Apply2 Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
由 Juncheng 提交于
* Matmul Primitive * refine * fix cublasComputeType_t Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 19 10月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Fix BroadcastMatmulFactory * auto format by CI * int64_t*=> const int64_t* Co-authored-by: Noneflow-ci-bot <ci-bot@oneflow.org> Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 15 10月, 2021 1 次提交
-
-
由 Juncheng 提交于
* matmul api * BlasTransposeType * BatchMatmul/BroadcastMatmul * fix * fix * enum=>enum class Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 08 10月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Primitive based add kernel * refine * refine * include * create primitive in compute * fix sole input Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 01 10月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Primitive based cast kernel * refine * refine * include * create primitve in compute * typo Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 30 9月, 2021 2 次提交
-
-
由 Juncheng 提交于
* Add Scalar::Value * As=>Value Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
由 guo ran 提交于
* add memory_copy_nd primitive * rm log * reduce dim * auto format by CI * refine * refine * fix * merge master * refine * refine Co-authored-by: Noneflow-ci-bot <ci-bot@oneflow.org> Co-authored-by: NJuncheng <liujuncheng1022@gmail.com>
-
- 27 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
* PermutePrimitive * refine * refine * Refine movement size (#6417) * refine movement size * fix * refine * refine
-
- 23 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 18 9月, 2021 2 次提交
-
-
由 Juncheng 提交于
* Fill primitive * Set=>Fill * 1024=>1023 * Check CUDA_VERSION Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
由 Juncheng 提交于
* Refine Lamb * virtual=>override Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 17 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Add primitive * refine
-
- 13 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 11 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Add cast primitive * fix Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 09 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 08 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-
- 07 9月, 2021 1 次提交
-
-
由 Juncheng 提交于
* Add Primitive * #ifdef WITH_CUDA Co-authored-by: Noneflow-ci-bot <69100618+oneflow-ci-bot@users.noreply.github.com>
-