- 15 11月, 2022 2 次提交
-
-
由 jakpiase 提交于
* optimization for ln * fix * added output to gpd * added formatting * fix
-
由 Sławomir Siwek 提交于
* cleanup unused code * unify is_int8 is_bfloat16 * Simplify matmul_v2 FWD kernel * remove RunKernel methods * remove import namespace * remove headers * clean fluid/phi cross imports * remove fluid axpy_handler * delete fluid methods * activations * OneDNNMemDesc * MKLDNNFormatForSize * MatchShapeToLayout * MKLDNNMemoryFormat * MKLDNNFormat * ReorderMKLDNNHandler * to_void_cast * review suggestions * interpolate * remove fluid depedency
-
- 14 11月, 2022 1 次提交
-
-
由 yeliang2258 提交于
-
- 11 11月, 2022 2 次提交
-
-
由 czr-gc 提交于
* feat(ipu): add model_runtime backend support in IPU. * fix(ipu_executor): fix error message format. * fix(ipu_executor): fix format. * fix(ipu_executor): fix format again. * fix(ipu_executor): fix format again. * fix(ipu_executor): fix format again.
-
由 zyfncg 提交于
* generate static graph code for some ops by yaml * remove deleted files * update cmake * update cmake * udpate cmake
-
- 10 11月, 2022 3 次提交
-
-
由 zhangxin81 提交于
* add roformer pass&&plugin(novarlen)
-
由 wenbin 提交于
* skip_merge_layernorm * add UT * modify comments
-
由 RichardWooSJTU 提交于
* add fuse_multi_transformer_layer_pass
-
- 08 11月, 2022 3 次提交
-
-
由 Sławomir Siwek 提交于
* softplus+activation * fc + elementwise_add test refactored * rename MKLDNN to OneDNN * fc+activation tests refactored * remove softplus ut * whitespace * whitespace * codestyle * codestyle * add more cases to fc+act * remove softplus+hard_sigmoid pass * remove softplus + hard_sigmoid UT * add approximate for gelu * swish beta range * new codestyle * reduce number of tests
-
由 zhoutianzi666 提交于
* allow fold fill_constant && allow nms3 into trt in int8 model * use unordered_map * fix CI failing
-
由 Paulina Gacek 提交于
* Split kernel registered, tests for uint/int added * Split quantized * Split output scales calculated only once * NearestInterp test fix reversed * DequantizeOutputs corrected
-
- 07 11月, 2022 2 次提交
-
-
由 Hui Zhang 提交于
* suqeeze2 transpose2 fuse onednn * format * fix output shape * fix conflict * format * format * remove useless * remove log * simply pass * fix comment * fix * fix msg * fix error msg * format
-
由 Sławomir Siwek 提交于
* init changes * bnorm * method signature * change order * bnorm * removed unused args
-
- 04 11月, 2022 1 次提交
-
-
由 jakpiase 提交于
* tmp save * minor chnage * CI fix * added FC optimizations * latest update * CI fix * fixed bug with fusing fc
-
- 03 11月, 2022 3 次提交
-
-
由 yeliang2258 提交于
* add constant_folding_pass pass for mkldnn int8 * update UpdateScaleOpInOutScales
-
由 Sławomir Siwek 提交于
* add extra attr property set * add type_info for all context * add onednn context to all context * fix context compile error * simplify conv kernel args * pass runtime attr into dev_ctx * fix marco error * clear conv_grad_kernel extra args * merge conv_grad_grad into conv_grad * clear conv2d_grad_grad extra attrs * remove redundant imports * migrate softmax * clear yaml and eager extra attr * fix conv1d error * change to thread local * fix npu compile failed * try to fix windows compile failed * add conv2d onednn phi kernel * fix ci bugs (#36) * fix compile bugs (#38) * fix extra input transform bug (#39) * support dynamic created attr (#40) * reset extra info gen code * rm conv_grad_grad kernel * reimpl pass attr adapting * add int attr support * remove vector inputnames creating * merge dev * fix map at error * adjust attribute * adapt funcs to PHI Co-authored-by: NChen Weihang <chenweihang@baidu.com> Co-authored-by: NYuanRisheng <yuanrisheng@baidu.com>
-
由 wenbin 提交于
-
- 02 11月, 2022 1 次提交
-
-
由 丁一 提交于
-
- 01 11月, 2022 1 次提交
-
-
由 Kaipeng Deng 提交于
* fix memory copy in prepare_data. test=develop
-
- 31 10月, 2022 1 次提交
-
-
由 feng_shuai 提交于
* feat: add int8 support for vit * test:add test
-
- 27 10月, 2022 2 次提交
-
-
由 Leo Chen 提交于
* make all cpp tests dynamic linked to libpaddle.so * add comments * keep old cc_test for some tests * fix some ut * make some ut use cc_test_old * fix typos and fit for win32 * fix lib path * fix some tests * skip lite test * fit for rocm * fit for cinn * fit for mac * fit for win32 * skip inference ut * skip windows * fix coverage
-
由 Chen Weihang 提交于
* fix compile error of mkldnn * fix tensorrt error
-
- 26 10月, 2022 3 次提交
-
-
由 wenbin 提交于
* prelnlayernorm_shift * add ut * remove paddle_enforce * remove useless * add UT * remove UT * add UT * set timeout
-
由 Sławomir Siwek 提交于
* fc/matmuls + scale fuse pass * remove double-extension * add unit tests * comments from review * codestyle * add pass to int8 list * new codestyle * attr name typo
-
由 Chen Weihang 提交于
* remove using lodtensor part2 * resolve code format error * resolve conflict * resolve conflict * replace added frameworrk tensor
-
- 24 10月, 2022 1 次提交
-
-
由 yeliang2258 提交于
* fix log bugs * more fix * fix bugs
-
- 21 10月, 2022 1 次提交
-
-
由 Allen Guo 提交于
-
- 20 10月, 2022 2 次提交
-
-
由 Kaipeng Deng 提交于
* add fused_multi_transformer_encoder/decoder pass, run GPT-3 success
-
由 Sylwester Fraczek 提交于
-
- 19 10月, 2022 2 次提交
-
-
由 Ruibiao Chen 提交于
* Support stream overlap for c_allreduce_sum * Test CI * Add notes * Add SingleStreamGuard for BuildOpFuncList
-
由 WangZhen 提交于
* Fix recurrent op eager deletion pass error in dy2st * Polish code * Refine error message
-
- 18 10月, 2022 2 次提交
-
-
由 Wang Bojun 提交于
* first version, accuracy corrected * disable debug print * use blockReduceSum in phi * add UT * add opCompat * code style * code refine * bug fix * code refine * test fix * bugfix * codesytle fix * code style * code-style * code-style * code-style
-
由 Sławomir Siwek 提交于
* git * style * leave default relu in kernel * style * cleanup FCMKLDNN pattern * merge conflicts * update develop * update develop * add const * rename to oneDNN and adjust attributes * whitespace
-
- 17 10月, 2022 4 次提交
-
-
由 Wang Bojun 提交于
* first version of ln_s_p with s>0 * refine and UT * pass opt draft * pass opt * code refine * code-style * bug fix * fix ci test * code style
-
由 jakpiase 提交于
-
由 pangyoki 提交于
* skip ReplaceAllReduceOp in GraphtoBlock when nccl_ctxs_ is nullptr * update ut * test_dist_allreduce_op failed * fix test_dist_allreduce_op * add ut * fix nccl cpu compile * fix
- 16 10月, 2022 1 次提交
-
-
由 ZeKai Zhou 提交于
-
- 13 10月, 2022 2 次提交
-
-
由 yeliang2258 提交于
* fix immutable op quantize bugs * fix * fix build bug * fix test * notest,test=inference * fix ppyoloe acc drop bugs * fix test * fix test * add test * fix * fix * fix test * fix refined name bug * fix test * bias fix * fix matmul weight dequant bug * re-ci * fix tester * fix test * fix tester * update weight dequantize func * update code * update test for converage * update test * update cmake * update cmakelist * update code * rerun ci * remove useless code
-
由 joanna.wozna.intel 提交于
* Add unsigned int8 propagation * Add or modify unit tests * Correct concat scale checking * Apply review suggestions * Corrections
-