lzhengning
/
JittorMirror
mirror of https://github.com/Jittor/Jittor
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
2,034 Commits 57 Branches 331 Tags 26 MiB
Commit Graph

1596 Commits

Author SHA1 Message Date
CHEN Xinsheng 3d06d25077 add ACL op `any` 2024-11-12 10:32:07 +08:00
CHEN Xinsheng a0dfdc5ff0 add `getitem` (`None` case) 2024-11-11 21:33:55 +08:00
邓一轩 e0537e5c1a concat 2024-11-11 19:58:31 +08:00
邓一轩 58fc5a9b35 fix conv 2024-11-11 19:43:56 +08:00
邓一轩 495a26a458 add sync at end of all op 2024-11-11 17:09:22 +08:00
邓一轩 b9986ac53b use switch 2024-11-11 15:52:35 +08:00
CHEN Xinsheng c747053a54 fix `concat` 2024-11-09 20:13:47 +08:00
514flowey 382bd3f0e5 update optimizer 2024-11-05 14:14:10 +08:00
CHEN Xinsheng 4e4e67dfd5 fix `nonzero` 2024-11-05 12:46:00 +08:00
dengyx21 810af5953b Revert "sync only on broadcast_to from [1]" 
This reverts commit 1439a03fca.
 2024-11-05 11:29:10 +08:00
CHEN Xinsheng 33bd28fdb3 add ACL op `where` (unary case) 2024-11-04 22:41:16 +08:00
CHEN Xinsheng 19d2e2e912 add ACL op `nonzero`, a temporary implementation, a bit slow 2024-11-04 22:38:29 +08:00
dengyx21 1902dab9c5 sync only on broadcast_to from [1] 2024-11-04 19:42:09 +08:00
CHEN Xinsheng f79e2908ed Merge pull request #3 from CSCG-Lab/jtorch 
fix some bugs for jtorch
 2024-10-30 12:34:08 +08:00
dengyx21 158ec0756c shut off a stream 2024-10-29 20:14:41 +08:00
CHEN Xinsheng b279960344 Merge branch 'main' 2024-10-29 15:42:39 +08:00
DongYang Li 56bc5f65be fix jt.index error 2024-10-24 02:32:02 +08:00
CHEN Xinsheng f34e1beafa fix warp (class case) 2024-10-21 20:39:15 +08:00
CHEN Xinsheng 1776dd4da9 fix warp (class case) 2024-10-21 17:08:01 +08:00
CHEN Xinsheng 8a31c402de fix `jt.index` 2024-10-18 17:18:06 +08:00
CHEN Xinsheng 811dc241d4 fix `jt.Var.triu_` 2024-10-18 11:13:32 +08:00
CHEN Xinsheng 17048da065 fix finfo & iinfo 2024-10-17 22:00:22 +08:00
CHEN Xinsheng cf4ce2c95e fix finfo bug in jittor 2024-10-17 21:36:00 +08:00
CHEN Xinsheng 89010f5475 fix `Var.triu` & `Var.triu_` 2024-10-17 21:24:19 +08:00
CHEN Xinsheng 6edc1f74a3 add cub_cumsum & cumprod 2024-10-17 21:23:32 +08:00
CHEN Xinsheng c886f01b53 fix warp (class case) 2024-10-17 21:22:26 +08:00
lidongyang fc1fff8c0e update version to 1.3.9.11 2024-10-08 23:03:24 +08:00
lidongyang 72be1396d9 fix: jupyter restart error 2024-10-08 23:02:27 +08:00
zjp_shadow 8966ca4320 fix transpose 2024-10-06 21:20:12 +08:00
uyzhang a078268e18 polish 2024-10-01 19:34:51 +08:00
uyzhang 33898421e4 Merge branch 'main' of https://github.com/CSCG-Lab/JittorHW into main 2024-10-01 18:16:47 +08:00
uyzhang 4c6d726a4c Refactor transpose_acl function and fix bug in matmul_acl 2024-10-01 18:14:08 +08:00
张仪 cb75c8dedd format 2024-09-29 13:47:22 +08:00
uyzhang c268a0bfaf Refactor aclnn.h and acl_op.h to add support for FlashAttention and FlashAttentionBackward 2024-09-29 12:29:41 +08:00
uyzhang 146574d7d1 Refactor transpose_acl function and fix bug in matmul_acl 2024-09-27 19:47:13 +08:00
uyzhang 4329f3b287 Refactor transpose_acl function and fix bug in matmul_acl 2024-09-27 19:44:04 +08:00
zjp_shadow b48d8664a1 add transpose 2024-09-27 19:37:19 +08:00
uyzhang c7c7326456 fixed the bug in matmul 2024-09-27 16:54:43 +08:00
zjp_shadow d648713ec5 Update concat 2024-09-25 00:37:36 +08:00
uyzhang 934885c96e Merge branch 'main' of https://github.com/CSCG-Lab/JittorHW into main 2024-09-23 23:12:49 +08:00
uyzhang dc29fa69dc FEAT! opt transpose in matmul and bmm 2024-09-23 23:12:44 +08:00
uyzhang c3df41e77b Refactor acl_compiler.py to handle gradient accumulation in bmm_acl and matmul_acl functions 2024-09-23 23:11:04 +08:00
uyzhang d092b83d0b Merge branch 'main' of https://github.com/CSCG-Lab/JittorHW into main 2024-09-23 22:43:47 +08:00
uyzhang 74aa4e68c2 Refactor acl_compiler.py to handle gradient accumulation in bmm_acl and matmul_acl functions 2024-09-23 22:43:44 +08:00
uyzhang 7fa22e2e32 add Ellipsis 2024-09-23 22:27:44 +08:00
uyzhang 9578e30972 Refactor acl_compiler.py to handle gradient accumulation in bmm_acl and matmul_acl functions 2024-09-23 20:40:53 +08:00
uyzhang 37671ccec1 Refactor acl_compiler.py to handle gradient accumulation in bmm_acl and matmul_acl functions 2024-09-23 20:26:46 +08:00
uyzhang 657687e0c0 Refactor acl_compiler.py to handle gradient accumulation in bmm_acl and matmul_acl functions 2024-09-23 16:09:42 +08:00
uyzhang 2a142ae73d fix bug of setitem cpu when use acl 2024-09-23 15:34:45 +08:00
uyzhang 9907aad7de fix getitem&setitem slice bug 2024-09-23 13:58:37 +08:00
uyzhang 2c2e8abe59 fix slice setitem 2024-09-23 13:18:49 +08:00
uyzhang 0d5035443e fix setitem not in graph 2024-09-23 03:26:12 +08:00
uyzhang fa288cb4d9 Refactor acl_op.h to use __fp16 for alphaValue in the case of ACL_FLOAT16 dtype 2024-09-22 18:06:38 +08:00
uyzhang 9ff62acf7d Refactor acl_op.h to use __fp16 for alphaValue in the case of ACL_FLOAT16 dtype 
Refactor grad method for improved performance and synchronization
Index indices to int32
Fix getitem bug
Add getitem&setitem mask
 2024-09-22 16:41:43 +08:00
lidongyang 8888b25ea7 fix getitem bug 2024-09-22 02:30:16 +08:00
lidongyang 464009af42 add getitem&setitem mask 2024-09-21 22:57:54 +08:00
uyzhang a357a7913d Refactor acl_op.h to use __fp16 for alphaValue in the case of ACL_FLOAT16 dtype 2024-09-21 17:17:47 +08:00
uyzhang 631a9a3aaa Refactor grad method for improved performance and synchronization 2024-09-21 14:20:10 +08:00
lidongyang 0705ed9d8f index indices to int32 2024-09-20 22:10:15 +08:00
uyzhang 015bd10210 Refactor flip and squeeze operations for improved performance and synchronization 2024-09-20 21:54:49 +08:00
lidongyang 898ec600b4 polish getitem&setitem 2024-09-20 21:44:47 +08:00
lidongyang babd92a002 polish getitem&setitem -1 2024-09-20 20:01:45 +08:00
lidongyang cdad66c01d polish output dtype 2024-09-20 19:43:56 +08:00
张仪 18afb843ad Fix synchronization issue in acl_op.h 2024-09-19 19:52:25 +08:00
张仪 4006f242de fixed bugs 2024-09-18 17:33:23 +08:00
张仪 e47a74a497 Fix broadcasting issue in acl_compiler.py and add support for setting item in jt.Var 2024-09-14 16:00:15 +08:00
lidongyang 651b24e634 add sigmoid embedding silu 2024-09-13 03:19:25 +08:00
lidongyang 0641a50a5d change op file to acl_op.h 2024-09-12 22:29:20 +08:00
lidongyang e00e4f099c add getitem&setitem 2024-09-12 20:25:48 +08:00
张仪 c55d49a8de add new aclop 2024-09-12 20:14:22 +08:00
张仪 3beeec78b1 add new aclop & fixed some bugs 2024-09-12 17:11:23 +08:00
张仪 eb89ae19ed add new aclop 2024-09-07 22:11:39 +08:00
张仪 21580ce80e update aclnn 2024-09-07 18:18:00 +08:00
范孙奇 2c141fa996 fix dim=3 error 2024-09-05 20:14:36 +08:00
DongYang Li 4b907d493c Merge pull request #584 from liylo/module 
Make forward hook modifiy the inputs and outputs
 2024-09-04 16:33:04 +08:00
DongYang Li 79527c40e9 Merge pull request #583 from liylo/func 
Add support for block diag function
 2024-09-04 16:32:45 +08:00
DongYang Li a1fcd0f337 Merge pull request #503 from 514flowey/attention_mask 
add attention mask
 2024-09-04 16:19:46 +08:00
DongYang Li 96b97ccf55 Merge pull request #549 from fansunqi/bilinear 
check input1 and input2 shape in jt.nn.Bilinear()
 2024-09-04 16:16:31 +08:00
DongYang Li 818edc962e Merge pull request #558 from fansunqi/Upsample 
check input shape and scale factor's positiveness in jt.nn.Upsample
 2024-09-04 16:16:18 +08:00
DongYang Li 60d4f5a2ef Merge pull request #582 from liylo/master 
fix load_parameter for Parameterlist issue Jittor#581
 2024-09-04 16:15:49 +08:00
lidongyang 30b8a637de remove compatibility 2024-09-04 16:11:51 +08:00
liylo df442516ab forward hooks now could modifiy inputs and outputs 2024-08-28 21:35:12 +08:00
liylo 949c6ed676 init 2024-08-28 21:27:02 +08:00
liylo 1c5519acf2 simple implementation for block diag with proper grad 2024-08-28 21:18:56 +08:00
liylo c8ca6d30eb simple implementation for block diag 2024-08-28 21:13:00 +08:00
liylo ddaf3520e3 fix load 2024-08-28 20:50:37 +08:00
514flowey 1fbd56bb6d fix unique bug 2024-08-22 12:53:03 +08:00
张仪 b4244090ae first commit 2024-08-21 22:15:12 +08:00
514flowey 822955ac00 add several ffunctions 2024-08-20 15:08:19 +08:00
Yuxuan Han 1c0cf4c2e4 complement of test_aclop: error of scatter()-multiple and where() 2024-08-12 19:50:29 +08:00
Yuxuan Han b46264b9f8 complement of test_aclop 2024-08-12 19:28:01 +08:00
Yuxuan Han f353b18472 complement of test_aclop 2024-08-01 16:00:00 +08:00
Yuxuan Han 4deb69c4e5 Merge pull request #1 from Jittor/master 
Fixed the BUG of ACL op memory
 2024-07-26 21:20:43 +08:00
Yuxuan Han 550ca96a75 complement of test_aclop 2024-07-26 21:16:09 +08:00
张仪 c25ac3a4e8 Fixed the BUG of ACL op memory 2024-07-25 15:54:57 +08:00
hanyx 69b6dd3b42 Merge remote-tracking branch 'upstream/master' 2024-07-24 21:18:52 +08:00
Yi Zhang 496b771211 Update acl_compiler.py 2024-07-24 16:20:02 +08:00
Yi Zhang 29f2fbd853 Update compile_extern.py 2024-07-24 15:43:19 +08:00
张仪 53327feff2 feat: enable ACL optimization in split function 2024-07-24 15:25:10 +08:00
邓一轩 a755d64f9e FEAT! add floor_int 2024-07-24 15:13:57 +08:00
Yi Zhang 279e4113f3 Update compile_extern.py 2024-07-24 15:01:30 +08:00
Yi Zhang 140b17b824 Update acl_compiler.py 2024-07-24 14:53:04 +08:00
Yi Zhang 67d79a66d4 Merge pull request #572 from dengyx21/dev-dyx 
FEAT! add aclop unittest
 2024-07-19 17:05:00 +08:00
Yi Zhang 8a9c10d615 Format test_aclop.py 2024-07-19 17:04:42 +08:00
邓一轩 2b12e55447 FEAT! add aclop unittest 2024-07-19 17:01:17 +08:00
CHEN Xinsheng 9758b18c7d fix dtype mismatch in `nn.cross_entropy_loss` 2024-07-19 16:42:55 +08:00
邓一轩 8f6563cba9 FEAT! where,scatter,cumsum,gather,flip 2024-07-18 20:04:40 +08:00
lidongyang 121fee583d add no gpu device error 2024-07-12 15:07:35 +08:00
Jiapeng Zhang f7bc197200 fix load bugs 
fix load bugs of state
 2024-07-10 19:58:07 +08:00
hanyx fa8b332f32 ComplexNumber:polar,view_as_complex,view_as_real 2024-07-09 22:27:28 +08:00
Yi Zhang 3f0814b482 Update acl_compiler.py 2024-07-09 21:48:35 +08:00
张仪 2ae2f1d453 update acl 2024-07-09 19:50:35 +08:00
lidongyang 3b2ca1c2c0 Merge branch 'master' of https://github.com/Jittor/jittor 2024-07-09 14:28:57 +08:00
lidongyang a58c8c7988 polish nn.Sequential __getattr__ 2024-07-09 14:28:17 +08:00
DongYang Li 914cd170b4 Merge pull request #548 from fansunqi/binary_cross_entropy_with_logits 
check target and output shape in jt.nn.binary_cross_entropy_with_logits
 2024-07-08 17:16:26 +08:00
DongYang Li 6736ce68e3 Merge pull request #553 from fansunqi/conv_transpose3d 
modify stride positive check in jt.nn.conv_transpose3d/jt.nn.conv_transpose; add input shape check in jt.nn.conv_transpose3d/jt.nn.conv_transpose
 2024-07-08 17:15:38 +08:00
DongYang Li dde745407e Merge pull request #554 from fansunqi/ConvTranspose 
check stride positiveness and input shape in jt.nn.ConvTranspose
 2024-07-08 17:14:05 +08:00
DongYang Li 133307627e Update nn.py 2024-07-08 17:13:32 +08:00
DongYang Li 9983779d7a Merge pull request #551 from fansunqi/Conv1d_sp 
check input shape in jt.nn.Conv1d_sp
 2024-07-08 17:08:33 +08:00
DongYang Li bdd6bb6de5 Merge pull request #550 from fansunqi/Conv1d 
check input shape in jt.nn.Conv1d
 2024-07-08 17:07:57 +08:00
DongYang Li 2b57b2d988 Merge pull request #555 from fansunqi/Dropout2d 
check input shape in nn.Dropout2d
 2024-07-08 17:05:49 +08:00
DongYang Li c669b1219a Merge pull request #556 from fansunqi/zeroPad2d 
check input shape in jt.nn.ZeroPad2d
 2024-07-08 17:05:22 +08:00
JittorRepos 596368ae7c Merge pull request #557 from fansunqi/ReplicationPad2d 
check input shape in jt.nn.ReplicationPad2d
 2024-07-08 17:04:21 +08:00
JittorRepos 98d7c2d0fa Merge pull request #562 from fansunqi/unfold 
check parameter's positive in jt.nn.Unfold
 2024-07-08 17:03:02 +08:00
lidongyang c47549e673 add isin 2024-07-05 18:12:43 +08:00
DongYang Li dcd6c6b2be update version 2024-07-02 20:02:02 +08:00
fansunqi f4d4c9d55c check parameter's positive in jt.nn.unfold 2024-07-01 15:41:24 +08:00
Sunqi Fan c45dac35e6 Merge branch 'Jittor:master' into fold 2024-07-01 12:26:35 +08:00
fansunqi 45ccf3d2ac check parameters' positive in jt.nn.fold 2024-07-01 12:23:03 +08:00
DongYang Li 4196cb8154 update version 2024-06-25 16:49:44 +08:00
范孙奇 f358fb7518 check input shape and scale factor's positiveness in jt.nn.Upsample 2024-06-10 19:27:29 +08:00
范孙奇 969d810f55 resume 2024-06-10 19:26:40 +08:00
范孙奇 78b7cf091b check input shape and scale factor's positiveness in jt.nn.Upsample 2024-06-10 19:25:53 +08:00
范孙奇 c4480b7e3b check input shape in jt.nn.ReplicationPad2d 2024-06-10 19:08:53 +08:00
范孙奇 d31b0a244d check input shape in jt.nn.ZeroPad2d 2024-06-10 19:05:49 +08:00
范孙奇 1fba329474 check input shape in nn.Dropout2d 2024-06-10 17:02:05 +08:00
范孙奇 958708ed60 modify error information 2024-06-10 16:48:27 +08:00
范孙奇 e6e5949765 add stride check in jt.nn.ConvTranspose 2024-06-10 16:45:53 +08:00
范孙奇 2266d21a8b remove 3D(unbatch) description 2024-06-10 16:43:22 +08:00
范孙奇 db8fcb33da modify stride positive check in jt.nn.conv_transpose; add input shape check in jt.nn.conv_transpose 2024-06-10 16:39:05 +08:00
范孙奇 baf6b45cf1 add input shape check in jt.nn.transpose3d 2024-06-10 16:29:58 +08:00
范孙奇 8fd834465c modify stride positive check in jt.nn.transpose3d 2024-06-10 16:08:48 +08:00
范孙奇 ae0e52dca5 check input shape in jt.nn.ConvTranspose 2024-06-06 20:55:46 +08:00
范孙奇 d895cb9d36 jt.nn.Conv1d in_channels and out_channels must be positive 2024-06-06 20:39:10 +08:00
范孙奇 b4155d8021 jt.nn.Conv1d_sp in_channels and out_channels must be positive 2024-06-06 20:35:05 +08:00
范孙奇 a42198705b check input shape in jt.nn.Conv1d_sp 2024-06-06 20:25:29 +08:00
范孙奇 4d11325634 check input shape in jt.nn.Conv1d 2024-06-06 20:18:31 +08:00
范孙奇 7f6beb58b9 check input1 and input2 shape in jt.nn.Bilinear() 2024-06-06 20:04:35 +08:00
范孙奇 2f11e3bbbe check target shape and output shape in jt.nn.binary_cross_entropy_with_logits 2024-06-06 18:02:29 +08:00
lidongyang 393684f196 polish nn.Sequential attribute 2024-06-05 22:31:20 +08:00