- Jan 04, 2018
-
-
Yizhi Liu authored
-
- Jan 03, 2018
-
-
masahi authored
* rocblas integration * fix include * fix lint
-
- Jan 02, 2018
-
-
masahi authored
* add cublas support * integrate cublas to topi dense * add cublas error check * minor fix * fix lint * remove topi import from contrib unittest
-
- Dec 29, 2017
-
-
masahi authored
* use cudnn findalgo to choose the best algo * fix lint
-
- Dec 27, 2017
-
-
Xingjian Shi authored
* support dim-0 tensor in topi ops revert transform * revert
-
masahi authored
* add target.libs to target str representation * integrate cudnn into topi cuda * append target.libs to target.options
-
- Dec 26, 2017
-
-
masahi authored
* add extern schedule for miopen * fix comment * optionally dispatch to miopen from topi * fix lint * check if current target is None * use generic dispatch for rocm conv2d * fix lint * fix workspace bug * remove blank line * remove blank line * remove blank line
-
- Dec 25, 2017
-
-
Yuwei Hu authored
* add x86_64 target * add binary dense operator * rebase * improve schedule * remove x86 target * improve schedule
-
- Dec 04, 2017
-
-
Tianqi Chen authored
* Support rank-0 tensor * fix lint
-
- Nov 27, 2017
-
-
ziheng authored
-
- Nov 25, 2017
-
-
Tianqi Chen authored
* [PASS] Allow compact checking when strides is available * remove assert compact
-
- Nov 19, 2017
-
-
Leyuan Wang authored
* scheduler tweaked for super resolution perf * conv2d_transpose schedule error fixed * nnvm issue #239 fixed
-
- Nov 16, 2017
-
-
Leyuan Wang authored
* scheduler tweaked for super resolution perf * lint error fixed * lint error fixed * conv2d_transpose schedule error fixed
-
- Nov 14, 2017
-
-
ziheng authored
* [TOPI] Add out_dtype argument for conv2d; Add x86 schedules * Fix * Fix lint * Fix
-
Leyuan Wang authored
* conv2d perf improved for conv2d_56_64_128, test name added to differentiate workloads * fix lint error
-
- Nov 13, 2017
-
-
abergeron authored
* Make the tvm conda package build with in-place source and use cmake from conda. * Add a package for topi.
-
- Nov 09, 2017
-
-
Yizhi Liu authored
-
- Nov 08, 2017
-
-
Leyuan Wang authored
-
- Nov 06, 2017
-
-
Yuwei Hu authored
-
- Nov 03, 2017
-
-
Yuwei Hu authored
-
- Oct 30, 2017
-
-
Leyuan Wang authored
-
- Oct 27, 2017
-
-
Tianqi Chen authored
-
- Oct 26, 2017
-
-
masahi authored
-
- Oct 25, 2017
-
-
Yuwei Hu authored
-
- Oct 23, 2017
-
-
masahi authored
* update topi/cuda schedules to use target.max_num_threads * allow num_thread to be larger than cuda.max_num_threads * remove get_max_num_threads and make it inline
-
- Oct 22, 2017
-
-
Tianqi Chen authored
-
- Oct 15, 2017
-
-
Tianqi Chen authored
-
- Oct 14, 2017
-
-
Tianqi Chen authored
* [TVM] Introduce target generic dispatch system * fix target warning
-
masahi authored
-
- Oct 13, 2017
- Oct 06, 2017
-
-
Xingjian Shi authored
* add argmax argmin * remove coder saver
-
Leyuan Wang authored
* conv2d tweaked for better end-to-end performance * syntax changed
-
Leyuan Wang authored
* conv2d layout change bug fixed * remove debug msg * misaligned error fixed
-
- Oct 05, 2017
-
-
Leyuan Wang authored
-
- Oct 03, 2017
-
-
ziheng authored
* [TOPI] Add left_shift, right_shift, clip, cast * [TOPI] Add test * [TOPI] Fix
-
- Sep 30, 2017
-
-
Tianqi Chen authored
-
ziheng authored
-
- Sep 29, 2017
-
-
Tianqi Chen authored
* [DOCS] How to deploy TVM Modules * More comments
-
- Sep 28, 2017
-
-
Xingjian Shi authored
-