- 14 9月, 2021 7 次提交
-
-
由 JYChen 提交于
-
由 Zeng Jinle 提交于
* fix raw optimizer gm * update * update ut
-
由 chenenquan 提交于
* Add empty_cache api to release idle gpu memory hold by allocator,test=develop * Add empty_cache api to release idle gpu memory hold by allocator,test=develop * Add empty_cache api to release idle gpu memory hold by allocator,test=develop * Fix test coverage problem for empty_cache * delete redundant check for empty_cache * fix the problem of empty_cache's doc * delete the nvidia-smi comment in doc of empty_cache, test=document_fix
-
由 石晓伟 提交于
-
由 tianshuo78520a 提交于
Update git clone model-benchmark CI
-
由 Wilber 提交于
-
由 WeiXin 提交于
-
- 13 9月, 2021 31 次提交
-
-
由 YUNSHEN XIE 提交于
-
由 danleifeng 提交于
-
由 YUNSHEN XIE 提交于
-
由 YUNSHEN XIE 提交于
* Change uts to nightly mode * remove test_trt_pool_op from parallel_UT_rule.py,test=document_fix
-
由 Yiqun Liu 提交于
Revert "Implement FunctionTraits to support two kinds of elementwise functor and remove some old codes for broadcast. (#35487)" (#35686)
-
由 xiaoting 提交于
* fix interpolate launch error, test=develop * fix area mode for interp, test=develop
-
由 ceci3 提交于
* fix instance norm index error * add unittest * update * fix
-
由 tianshuo78520a 提交于
Fix CPU CI build-time
-
由 Yiqun Liu 提交于
Implement FunctionTraits to support two kinds of elementwise functor and remove some old codes for broadcast. (#35487)
-
由 xiongkun 提交于
-
由 taixiurong 提交于
-
由 hlygit66666 提交于
* fix cumprod docs * fix cumprod op docs; test=document_fix
-
由 zhulei 提交于
* [RC22] Fix linear with matmul_op replace * [RC22] Fix linear with matmul_op replace * [RC22] Fix linear with matmul_op replace * [RC22] Fix linear with matmul_op replace * [RC22] Fix linear with matmul_op replace
-
由 baoachun 提交于
* add flatten/flatten2 converter test cases * add fatten/flatten2 trt converter test cases
-
由 JZ-LIANG 提交于
* reshape support zero-input * add unitest * revise error message
-
由 李季 提交于
* upload global scatter and global gather operators related files
-
由 Zhang Zheng 提交于
-
由 baoachun 提交于
-
由 baoachun 提交于
-
由 Qi Li 提交于
-
由 Yanxing Shi 提交于
* fix github name * fix CI error * fix review and CI error * fix inf,nan error and modify unittest samples * add unittest samples * add unittest samples * fix unittest error * test=document_fix * test=document_fix * modify doc and add unittest samples * fix error newline in constant * modify doc after mentor review * modify __all__ and doc * modify doc
-
由 ShenLiang 提交于
* support grad group * fix single card condition
-
由 Siming Dai 提交于
-
由 baoachun 提交于
* add group_norm trt converter test case * update group_norm trt converter test case
-
由 chentianyu03 提交于
This reverts commit ae93d9c2.
-
由 JYChen 提交于
-
由 Guoxia Wang 提交于
* support hybrid parallel inference helper class
-
由 zhulei 提交于
* [ROCM] fix top_k_v2 with large shape * [ROCM] fix top_k_v2 with large shape
-
由 lidanqing 提交于
-
由 jakpiase 提交于
* implemented clip op bf16/fp32 * added skipping if not cpu or bf16 * CI rerun after bf16 package change * added parentheses to ensure formatting
-
由 joanna.wozna.intel 提交于
-
- 12 9月, 2021 1 次提交
-
-
由 王明冬 提交于
-
- 11 9月, 2021 1 次提交
-
-
由 wanghuancoder 提交于
* refactor gc, test=develop * refine, test=develop * refine, test=develop * refine, test=develop * gc each tensor, test=develop * refine, test=develop
-