- 17 2月, 2023 13 次提交
-
-
由 xiaoguoguo626807 提交于
-
由 whisky-12 提交于
-
由 Aurelius84 提交于
-
由 Ruibiao Chen 提交于
* Consider kernel argument def for data device transform in standalone executor * Fix ALL_BACKEND errors * Fix CI errors
-
由 xiongkun 提交于
-
由 jiangcheng 提交于
-
由 risemeup1 提交于
-
由 risemeup1 提交于
-
由 risemeup1 提交于
-
由 wangzhen38 提交于
* [RM FLUID] rm fluid_pslib_init * [RM FLUID] for ci * [RM FLUID] for ci
-
由 YUNSHEN XIE 提交于
* add cinn_git_tag param * fix format error
-
由 Aurelius84 提交于
* [Dy2St]Remove PE logic in @to_static * fix typo * fix infer_program * fix typo * fix op_size
-
由 xiaoguoguo626807 提交于
* add approve rules * add attr
-
- 16 2月, 2023 24 次提交
-
-
由 joanna.wozna.intel 提交于
* Add matmul_v2 to the quantization process and adjust Ernie model test * Correct cpu_quantize_pass test * Move op to fuse transformation to placement pass * Correct test
-
由 HongyuJia 提交于
* fix py::array_t calling bug * polish test_phi_tensor * stop fix inference bug in this PR * polish unittest * change int->int32_t * fix unittest * fix compile error * modify cmake * remove redundancy codes * fix selectedRow unittest * fix cmake relay * declare kernel
-
由 whs 提交于
-
由 cyber-pioneer 提交于
-
由 xiongkun 提交于
* [dy2static-bugfix] fix backward gradient aggregation bugs 1. Yolov3 and Yolov5 all face the same problem. * remove set_device * code review fix
-
由 Hulek 提交于
* New onednn test * checkopoint * added new test, fixed issue with onednn bias * fix bias check * remove prints, refactor code * delete old test * update python tests cmake * Delete depracated conv bias * Delete outdated bias from convolution test
-
由 Tomasz Socha 提交于
-
由 Chen Weihang 提交于
* add logspace yaml * update by comments * resolve test framework conflicct
-
由 chalsliu 提交于
-
由 whs 提交于
Add PTQ and exporting function 1. Add Post-Training Quantization 1.1 Abstract some functions from QAT to Quantization class 1.2 Add Post-Training Quantization by extending Quantization class 1.3 Add observers for PTQ 1.4 Add unittest for PTQ 2. Add exporting function for QAT and PTQ
-
由 shentanyue 提交于
* support xpu multi-card infer * add ut * clean code * clean code * fix * fix * fix * fix
-
由 HongyuJia 提交于
* polish namespace * change static_tensor_operants * polish namespace * support add, subtract, divide * add unit test * polish unittest * fix cmake error * polish unittest
-
由 Leo Chen 提交于
-
由 risemeup1 提交于
-
由 zyfncg 提交于
-
由 Aurelius84 提交于
-
由 houj04 提交于
* [XPU] update xccl to 1.0.8 * update xdnn. add uint8 for concat and split. * update xdnn to 20230215.
-
由 ronnywang 提交于
* [XPU] add group_norm kernel * update * add xpu sin, cos, randint, linspace kernels * update * update
-
由 Huang Jiyi 提交于
* move layer_norm_kernel.cu.h to phi * fix bugs * fix namespace * fix bugs * fix CI-Windwos * replace mutable_data * fix bugs * fix bugs
-
由 zhupengyang 提交于
-
由 Ruibiao Chen 提交于
* Use StandaloneExecutor in FleetExecutor * Update FLAGS * Fix CI errors * Update code * Add force_root_scope_vars config * Update code * Fix CI errors * Fix test_layer_new errors
-
由 Huang Jiyi 提交于
* move variable_utils from phi_api_utils to fluid * fix coment * update include * fix bugs * fix bugs * fix bugs * fix bugs * fix bugs * update * update * fix CI-Windows-OpenBLAS * fix bugs * fix bugs * fix bugs * update include * move variable_utils to phi_utils * fix namespace
-
由 姜永久 提交于
* disable unewanted dygraph tests * mine_hard_exa
-
由 zqw_1997 提交于
* beta * small commit * add batch_norm composite rule move composite test case remove unuseful var add composite op blacklist * small change v2 * finish the test_composite_mean and test_composite_mean_grad * add ops assertion to the tests * add cinn test * fix the error and inappropriate usage in func: mean_composite * remove the ref of outer lib in primtives.py * modify sample code of reduce_sum * fix composite mean op map * modify testcases to test more float type * remove cpu float16 test * cinn test fix * remove reduce_max * change the name sum to sum_x * change the use of reduce_sum to sum --------- Co-authored-by: Ncyber-pioneer <chenzhuo@tju.edu.cn>
-
- 15 2月, 2023 3 次提交
-
-
由 duanyanhui 提交于
-
由 niuliling123 提交于
-
由 Leo Chen 提交于
* make cinn_launch_op run interpretercore in tracing mode to reduce number of threads * skip getWorkqueue in tracing mode
-