- 13 6月, 2023 9 次提交
-
-
由 石晓伟 提交于
-
由 xiaoguoguo626807 提交于
* mutiply_triple delete * add case * add timeout
-
由 kangguangli 提交于
-
由 NetPunk 提交于
-
由 周周周 提交于
* forbid fp64 enter into trt
-
由 xiongkun 提交于
-
由 hong 提交于
* add kernel dialect * change DenseTensorTypeStorage to DenseTensorType * add test case` * add first pd_op to kernel dialect * lower pd op to kernel dialect * update * update * remove useless code * add attrite print test * fix bug * polish code
-
由 winter-wang 提交于
-
由 bukejiyu 提交于
* layer_norm op with dynamic shape support INormalizationLayer in TRT8.6 * Using trt layer to make layers_norm op in lower than trt8.6 layer_norm op with dynamic shape support INormalizationLayer in TRT8.6
-
- 12 6月, 2023 10 次提交
-
-
由 winter-wang 提交于
-
由 kangguangli 提交于
* adapt_startup_program * refactor program translator * polish * add custom op printer hook * fix merge conflicts * fix top level op printer * adapt full int array op * modify by reviews * fix
-
由 Hui Zhang 提交于
* fix for log xxx * add int32/int64 for cpu/gpu; add float16/bfloat16 for cpu forward * fix docstring * fix bug * fix bugs * fix bugs * fix bugs * fix bugs * fix bug * using cast * fix test * fix api * fix other bugs * fix ci bug for not using dygraph guard * add bfloat16 test * fix ut * bf16
-
由 zhangbo9674 提交于
-
由 ShenLiang 提交于
-
由 YuanRisheng 提交于
* add phi option in cmake * modify default option * fix windows bugs * perfect log * change default mode * change phi so on for py3
-
由 risemeup1 提交于
-
由 Zhang Jun 提交于
* support bias's rank equal to input's rank
-
由 Nyakku Shigure 提交于
-
由 zhangbo9674 提交于
-
- 11 6月, 2023 2 次提交
-
-
由 huangjiyi 提交于
* “update” * update * update * update * update * test * update
- 10 6月, 2023 3 次提交
-
-
由 limingshu 提交于
-
由 HongyuJia 提交于
-
由 zhangbo9674 提交于
* fix ir storage bug * refine code * refine code * fix bug * refine code * refine code
-
- 09 6月, 2023 10 次提交
-
-
由 winter-wang 提交于
-
由 pangengzheng 提交于
* support add(x_float32, bfloa16_) or add(x_float32, y_float16) * polish * fix test
-
由 lzydev 提交于
* auto generate code for elementwise_max * auto generate code for elementwise_max * fix composite ops * fix bug of fmax
-
由 xiaoguoguo626807 提交于
* modify multiply_grad_node create * add place choose * segment fault modify
-
由 kangguangli 提交于
* adapt_startup_program * refactor program translator * polish
-
由 jiangfan06 提交于
-
由 zhangbo9674 提交于
* refine code * refine code * refine code * refine code * refine code * refine code * refine code * fix bug * refine code * refine code * refine code * refine code * refine code * delete unused code * delete unused code * refine code
-
由 zhupengyang 提交于
-
由 Nyakku Shigure 提交于
* bump ruff to 0.0.271 and update config * exclude third_party * bump ruff to 0.0.272 * refine config
-
由 houj04 提交于
-
- 08 6月, 2023 6 次提交
-
-
由 周周周 提交于
* remove redunant
-
由 jiangcheng 提交于
* [CINN] add paddle.device.is_run_with_cinn() api for running check * for pass ci converge * add check whl should compiled with cinn * fix ci coverage bug * remove exposed API * import is_run_with_cinn explicitly
-
由 wz1qqx 提交于
-
由 ykkk2333 提交于
-
由 Aurelius84 提交于
-
由 hong 提交于
* add kernel dialect * change DenseTensorTypeStorage to DenseTensorType * add test case`
-