InfiniTensor

Commit Graph

Author	SHA1	Message	Date
Bolun Zhang	fac28c25f6	添加 MLU 平台分布式验收脚本 (#223 ) * 添加 MLU 平台分布式验收脚本 * add fp16 test, fix cast * fix * add onnxsim for llama * add matmul tf32 for mlu * add submodule: onnxsim_large_model * fix * modified bang_launch.py, start_single * add test for albert/opt * change file path --------- Co-authored-by: xgqdut2016 <kenan_gewei@163.com>	2024-04-28 11:24:09 +08:00
PanZezhong1725	7f6aec6c17	针对bert和gpt2模型分布式推理的优化 (#221 ) * fix(dist): 改善分布式脚本，只打印绝对误差 * feat(dist): 增加可导出onnx的pytorch运行脚本 * feat(front): 增加对Y值为-inf的where算子的图优化 * feat(kernel): 对b为常数的pow和div算子进行特判优化 * fix(front): 消除前端对global output形状信息的依赖，分布式脚本删除不必要的shape infer * feat(kernel): 针对matmul中bias为行向量时的expand操作的特化优化 * fix(kernel): 删除div pow const中不必要的同步 * Update expand.cu * fix: fix comments --------- Co-authored-by: Haojie Wang <haojie0429@gmail.com> Co-authored-by: Derui Yang <ydrml@hotmail.com>	2024-04-01 14:04:28 +08:00

Author

SHA1

Message

Date

Bolun Zhang

fac28c25f6

添加 MLU 平台分布式验收脚本 (#223 )

* 添加 MLU 平台分布式验收脚本

* add fp16 test, fix cast

* fix

* add onnxsim for llama

* add matmul tf32 for mlu

* add submodule: onnxsim_large_model

* fix

* modified bang_launch.py, start_single

* add test for albert/opt

* change file path

---------

Co-authored-by: xgqdut2016 <kenan_gewei@163.com>

2024-04-28 11:24:09 +08:00

PanZezhong1725

7f6aec6c17

针对bert和gpt2模型分布式推理的优化 (#221 )

* fix(dist): 改善分布式脚本，只打印绝对误差

* feat(dist): 增加可导出onnx的pytorch运行脚本

* feat(front): 增加对Y值为-inf的where算子的图优化

* feat(kernel): 对b为常数的pow和div算子进行特判优化

* fix(front): 消除前端对global output形状信息的依赖，分布式脚本删除不必要的shape infer

* feat(kernel): 针对matmul中bias为行向量时的expand操作的特化优化

* fix(kernel): 删除div pow const中不必要的同步

* Update expand.cu

* fix: fix comments

---------

Co-authored-by: Haojie Wang <haojie0429@gmail.com>
Co-authored-by: Derui Yang <ydrml@hotmail.com>

2024-04-01 14:04:28 +08:00

2 Commits