- 30 5月, 2023 4 次提交
-
-
由 YuanRisheng 提交于
* fix compile error * delete code
-
由 RedContritio 提交于
* support auto generate for activation_op relu6 * add generated_static_op for activation_op in CMakeLists.txt
-
由 jameszhang 提交于
-
由 houj04 提交于
-
- 29 5月, 2023 4 次提交
-
-
由 Yuanle Liu 提交于
-
由 winter-wang 提交于
-
由 zhoutianzi666 提交于
-
由 wz1qqx 提交于
-
- 28 5月, 2023 1 次提交
-
-
由 kangguangli 提交于
* add op name normalizer * disable unittest
-
- 27 5月, 2023 1 次提交
-
-
由 张春乔 提交于
* rm , from \* @param(.*?), * Apply suggestions from code review * Apply suggestions from code review
-
- 26 5月, 2023 10 次提交
-
-
由 Leo Chen 提交于
* Copy QAT files from PaddleSlim * Integrate QAT API into Paddle * Replace eval function * Reduce test_quant_aware run time * Apply new formatter on modified files * Remove code check for Paddle version check * Copy quant_post_quant_aware UT from PaddleSlim * Integrate test_quant_post_quant_aware UT into PaddlePaddle * Apply new formatter on modified files * Remove redundant code and add unittests * Add new unittests * Update the time limit of new unittests
-
由 YuanRisheng 提交于
* create phi so * fix ci bugs * fix py3 bugs * add file * fix py3 bugs * fix windows bugs * perfect so * fix py3 bugs * delete all static target in phi * fix windows bugs * fix py3 bugs * fix ci bugs * fix windows bugs * fix bugs: gflags can't be linked by dynamic and static lib * fix bugs that can not load 3rd party * fix ci bugs * fix compile bugs * fix py3 bugs * fix conflict * fix xpu bugs * fix mac compile bugs * fix psgpu bugs * fix inference failed * deal with conflict * fix LIBRARY_PATH bug * fix windows bugs * fix onednn error * fix windows compile bugs * fix windows compile bugs * fix test_cuda_graph_static_mode_error aborted * fix windows bugs * fix mac-python3 error * fix hip compile bugs * change mode to static * change to static mode * fix ci bugs * fix py3 bugs * fix windows bugs * fix bugs * add static flag * add PADDLE_API * change position of PADDLE_API * fix windows bugs * change mode to dynamic lib * fix windows static bugs * deal with conflict * fix windows unit bug * fix coverage * deal with conflict * fix windows-inference * fix py3 bugs * fix bugs when compile type_info * fix compile bugs * fix py3 bugs * fix windows bugs * fix windows openblas * fix xpu bugs * fix enforce_test in windows * update code according comment * fix windows cmake bug * fix windows bugs * fix windows bugs * delete cinn unittest * fix cinn bugs --------- Co-authored-by: lzydev <1528794076@qq.com>
-
由 zhangbo9674 提交于
* on * add covrage for ir
-
由 zhaoyingli 提交于
* global view process_group * fix import * fix attr * fix tunner init comm
-
由 zhupengyang 提交于
* Not delete slice op if out op has shared var node
-
由 Yuanle Liu 提交于
* fix fp16 io * disable precision test
-
由 jiangfan06 提交于
-
由 risemeup1 提交于
* fix test error * fix test_exectuor_feed_non_tensor * fix test error
-
由 HongyuJia 提交于
-
由 Yuanle Liu 提交于
* [IR&PASS] part 1: add pass base, pass manager, adaptor pass, ut * include cstdint
-
- 25 5月, 2023 13 次提交
-
-
由 HongyuJia 提交于
-
由 Yuanle Liu 提交于
-
由 zhangkaihuo 提交于
-
由 zhangkaihuo 提交于
-
由 thunder95 提交于
-
由 zhangbo9674 提交于
* refine code * delete some unused code * refine code of build * refine code of build * add block * refine builder * refine code * refine code by comment * fix compiler bug
-
由 Zhang Jun 提交于
-
由 zhouweiwei2014 提交于
-
由 Leo Chen 提交于
* add log for memory stats * fix string_split in einsum
-
由 张春乔 提交于
-
由 ronnywang 提交于
-
由 houj04 提交于
-
由 zhoutianzi666 提交于
* add tranfer_elim * transfer layout elimination
-
- 24 5月, 2023 7 次提交
-
-
由 Leo Chen 提交于
-
由 Yiqun Liu 提交于
* Try to increase the repeat of autotune and fix the setting of allow_tf32_cublas. * Change the repeat of cublaslt to 10. * Use FLAGS_cublaslt_exhaustive_search_times as repeats. * Fix compiling error on CI. * Polish the key and simplify codes.
-
由 zhangyuqin1998 提交于
-
由 zhangyuqin1998 提交于
* move raw kernels to legacy * Update elementwise_add_kernel.cu * fix
-
由 zhangkaihuo 提交于
-
由 wz1qqx 提交于
-
由 Leo Guo 提交于
Fixed the bug in the api.cc file where there was an inconsistency between the specified type (std::vector<DenseTensor*>&) in the function pointer kernel_signature and the type of the phi kernel parameter (std::vector<DenseTensor*>) when the phi kernel is set to output as std::vector<DenseTensor*>. test=kunlun (#54053)
-