- 16 12月, 2020 4 次提交
-
-
由 Y_Xuan 提交于
* 添加rocm平台支持代码 * 修改一些问题 * 修改一些歧义并添加备注 * 修改代码格式 * 解决冲突后的代码修改 * 修改operators.cmake * 修改格式 * 修正错误 * 统一接口 * 修改日期
-
由 Zhang Ting 提交于
* improve grad perf
-
由 wangchaochaohu 提交于
-
由 WangXi 提交于
-
- 15 12月, 2020 10 次提交
-
-
由 chen.zhiyu 提交于
-
由 YUNSHEN XIE 提交于
* added UT should not exceed 15s * fix error * UT limit of 15s is the first to be executed * fix error * fix error with CI_SKIP_CPP_TEST * modfied tiemout setting * fix error
-
由 Chen Weihang 提交于
* add op test case for complex * polish code details * add xpu set constant support * fix argument rror * remove useless pyc file
-
由 AshburnLee 提交于
-
由 lijianshe02 提交于
* add transpose double grad test=develop
-
由 wangchaochaohu 提交于
-
由 Wilber 提交于
-
由 Zhou Wei 提交于
-
由 ShenLiang 提交于
* fix bug of matmul_v2 for broadcast
-
由 qingqing01 提交于
-
- 14 12月, 2020 10 次提交
-
-
由 wangchaochaohu 提交于
-
由 arlesniak 提交于
-
由 lilong12 提交于
-
由 WangXi 提交于
-
由 tangwei12 提交于
* add service, remove ut on mac * fix heter_profiler & add heter stop method * fix code style
-
由 Leo Chen 提交于
* fix compile problem when cuda_arch < 6000 * refine code * refine code
-
由 QingshuChen 提交于
* support roi_align & affine_channel for kunlun * minor
-
由 Huihuang Zheng 提交于
Fix 3 Windows Unittests test_fuse_all_reduce_pass: Paddle cannot run multiple-GPU on Windows so set single visible GPU flag test_feed_data_check_shape_type: Paddle cannot run multiple-GPU on Windows so set single visible GPU flag test_tsm: Winodws GPU size is not enough so decrease batch size and data size.
-
由 Jacek Czaja 提交于
-
由 GeminiCarrie 提交于
* Fix a bug when running on an operating system without "bash." * add execution condition * for ci-coverage * get cpu information to check the precision problem * Update compilation environment for musl version * update dependencies * remove test code check cpu info remove test code review * update alpine and third_party denpendencies * add newline for ci Code format
-
- 11 12月, 2020 10 次提交
-
-
由 Wilber 提交于
-
由 JZ-LIANG 提交于
* Sharding add hybrid-dp feature * update sharding in distributed_strategy * update sharding unitest * revise code format for sharding
-
由 Leo Chen 提交于
-
由 Zhang Ting 提交于
* improve drop out * add VectorizedRandomGeneratorWithGenerator * fix bug * modify according to comments
-
由 Zhang Ting 提交于
-
由 LoveAn 提交于
* Add the strategy of skipping cc/cu test compilation and execution in CI, test=develop * fix if error with CI_SKIP_TEST, test=develop * fix add properties to test error on Linux/MAC, test=develop * fix set test properties of test_code_generator error, test=develop * remove test codes and advance judgment of file modification on Linux, test=develop * rename CI_SKIP_TEST to CI_SKIP_CPP_TEST, test=document_fix * Add branch judgement on Linux, test=develop
-
由 Aurelius84 提交于
* Add more value to calculate hash key * fix size_t * polish code
-
由 taixiurong 提交于
* 1.fix matmul bug 2. add one hot * add xpu error msg
-
由 Jacek Czaja 提交于
* - Added infrastructre for new test - Added UT for Multiple models prediction - cosmetic fixes - lint - lint fixes * - Removed timeout for MMP test
-
由 joanna.wozna.intel 提交于
* Fix bf16 activations test for softmax and gelu * Resolve conflict
-
- 10 12月, 2020 6 次提交
-
-
由 Zhong Hui 提交于
fix p_norm with empty shape (#29500)
-
由 Zhou Wei 提交于
-
由 Leo Chen 提交于
* layernorm fw opt * layernorm bw opt * fix typo, test=develop * remove const dim3 for windows CI compatibility * merge develop Co-authored-by: Nzlsh80826 <zlsh80826@gmail.com>
-
由 arlesniak 提交于
* Flags assert condition more general, print output if pattern not found * removed test_flags_use_mkldnn form skip list regarding #29080 descr
-
由 tangwei12 提交于
* add ps table Change-Id: I468a04bd071d21ff52654926fcf4d5f3da19e178
-
由 chalsliu 提交于
-