Kuohais
/
GPUCodeForces
forked from ccf-ai-infra/GPUCodeForces
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
616 Commits 6 Branches 0 Tags 152 MiB
Commit Graph

616 Commits

Author SHA1 Message Date
ZZZJ f8b9bf230d fixes DwDilated1d #57 2025-12-09 17:55:23 +08:00
Kuohais cc73715277 Merge pull request 'feat:add high performance rmsnormresidual #32' (#355) from wut0n/GPUCodeForces:rmsnormresidual into main 2025-12-04 15:05:27 +08:00
Kuohais 37f154b016 Merge pull request 'feat:add high performance cosine+contrasstive #19' (#352) from wut0n/GPUCodeForces:cosinecontrasstive into main 2025-12-04 15:05:13 +08:00
Kuohais 0015859448 Merge pull request 'feat:add high performance focallossfuse #31' (#354) from wut0n/GPUCodeForces:focallossfuse into main 2025-12-04 15:04:58 +08:00
Kuohais 6632a0a634 Merge pull request 'finish relu-square #14' (#254) from Ljy123/GPUCodeForces:relusquare into main 2025-12-04 15:04:37 +08:00
Kuohais b314eaeb65 Merge pull request 'optimized affine-relu #13' (#255) from Ljy123/GPUCodeForces:optimized_affine into main 2025-12-04 15:03:11 +08:00
Kuohais 84dd0d8a37 Merge pull request 'finish softplus-bias #15' (#253) from Ljy123/GPUCodeForces:softplusbias into main 2025-12-04 15:02:53 +08:00
Kuohais d0a4ba59e4 Merge pull request 'finish bias-swish #11' (#257) from Ljy123/GPUCodeForces:biaswish into main 2025-12-04 15:02:43 +08:00
Kuohais cd61507f2e Merge pull request 'finish affine-relu #9' (#259) from Ljy123/GPUCodeForces:affine into main 2025-12-04 15:02:27 +08:00
Kuohais e361e752da Merge pull request 'finish softsign-affine #18' (#263) from Ljy123/GPUCodeForces:softsign into main 2025-12-04 15:02:17 +08:00
Kuohais 362e6e74a1 Merge pull request 'finish sigmoid-clamp-affine #15' (#252) from Ljy123/GPUCodeForces:sigmoidclamp into main 2025-12-04 15:01:53 +08:00
wut0n 2d69fa9275 feat:add high performance rmsnormresidual #32 2025-12-04 15:01:24 +08:00
Kuohais 4182053243 Merge pull request 'finish mish-bias #17' (#264) from Ljy123/GPUCodeForces:mishbias into main 2025-12-04 15:01:11 +08:00
Kuohais ee5383909e Merge pull request 'finish tanshrink affine #20' (#261) from Ljy123/GPUCodeForces:tanshrink-affine into main 2025-12-04 15:01:00 +08:00
Kuohais 7994a622c4 Merge pull request 'finish SoftExponential #20' (#269) from uucoco/GPUCodeForces:uucoco20 into main 2025-12-04 15:00:07 +08:00
wut0n 2e2b036748 feat:add high performance focallossfuse #31 2025-12-04 14:59:40 +08:00
Kuohais 8a48c19769 Merge pull request 'finish glu-fuse #12' (#256) from Ljy123/GPUCodeForces:glufuse into main 2025-12-04 14:59:25 +08:00
Kuohais f13470a1e6 Merge pull request 'finish LogSigmoid #23' (#272) from uucoco/GPUCodeForces:uucoco23 into main 2025-12-04 14:58:55 +08:00
Kuohais d49c5582f5 Merge pull request 'optimized sigmoid (power-sigmoid-gate) #21' (#260) from Ljy123/GPUCodeForces:power-sig into main 2025-12-04 14:58:41 +08:00
Kuohais 3d51e16fcb Merge pull request 'finish HardTanh #25' (#274) from uucoco/GPUCodeForces:uucoco25 into main 2025-12-04 14:58:24 +08:00
Kuohais 7df285023b Merge pull request 'finish HardSwish #26' (#275) from uucoco/GPUCodeForces:uucoco26 into main 2025-12-04 14:58:17 +08:00
Kuohais 70a747941d Merge pull request 'finish hardshrink #28' (#277) from uucoco/GPUCodeForces:uucoco28 into main 2025-12-04 14:58:10 +08:00
Kuohais 39c138857e Merge pull request 'finish HardSigmoid #27' (#276) from uucoco/GPUCodeForces:uucoco27 into main 2025-12-04 14:57:59 +08:00
Kuohais d212e8e916 Merge pull request 'fix:add high performance canberra #21' (#278) from wut0n/GPUCodeForces:canberra1 into main 2025-12-04 14:57:53 +08:00
Kuohais 51b4d5fda2 Merge pull request 'finish LogWeightedSumExp #22' (#271) from uucoco/GPUCodeForces:uucoco22 into main 2025-12-04 14:57:43 +08:00
Kuohais 9f47648552 Merge pull request 'finish LogMeanExp #24' (#273) from uucoco/GPUCodeForces:uucoco24 into main 2025-12-04 14:57:31 +08:00
Kuohais 93cac1f658 Merge pull request 'finish SoftClip #21' (#270) from uucoco/GPUCodeForces:uucoco21 into main 2025-12-04 14:57:06 +08:00
Kuohais 015d6c036b Merge pull request 'feat:add high performance Logsumexp #28' (#280) from wut0n/GPUCodeForces:logsumexp into main 2025-12-04 14:56:53 +08:00
Kuohais f6ddfb592e Merge pull request 'feat:add high performance Logbeta #29' (#281) from wut0n/GPUCodeForces:logbeta into main 2025-12-04 14:56:44 +08:00
Kuohais 88a7a59334 Merge pull request 'feat:add high performance sigmoid derivative #27' (#279) from wut0n/GPUCodeForces:sigmoid_derivative into main 2025-12-04 14:56:35 +08:00
wut0n ea98ae6c6e feat:add high performance cosine+contrasstive #19 2025-12-04 14:56:27 +08:00
Kuohais df2bbb43ef Merge pull request 'finish hardmish #36' (#287) from gsd123/GPUCodeForces:gsd36 into main 2025-12-04 14:56:16 +08:00
Kuohais 77e6cbc4db Merge pull request 'finish PDELU #37' (#288) from gsd123/GPUCodeForces:gsd37 into main 2025-12-04 14:56:05 +08:00
Kuohais 4e3c2aff4d Merge pull request 'finish Elish #35' (#286) from gsd123/GPUCodeForces:gsd35 into main 2025-12-04 14:55:54 +08:00
Kuohais 3805037ef6 Merge pull request 'finish CLL #41' (#292) from gsd123/GPUCodeForces:gsd41 into main 2025-12-04 14:55:47 +08:00
Kuohais 1b0443f980 Merge pull request 'finish CosLU #42' (#293) from gsd123/GPUCodeForces:gsd42 into main 2025-12-04 14:55:34 +08:00
Kuohais c01bbab562 Merge pull request 'finish Mish #31' (#282) from gsd123/GPUCodeForces:gsd31 into main 2025-12-04 14:55:26 +08:00
Kuohais 0fbada7a6c Merge pull request 'finish Adaptivepiecewiselinear #32' (#283) from gsd123/GPUCodeForces:gsd32 into main 2025-12-04 14:55:20 +08:00
Kuohais 6d8d2e6b8f Merge pull request 'finish ISRU #50' (#301) from gsd123/GPUCodeForces:gsd50 into main 2025-12-04 14:55:09 +08:00
Kuohais f16735bb3c Merge pull request 'finish Phish #38' (#289) from gsd123/GPUCodeForces:gsd38 into main 2025-12-04 14:54:58 +08:00
Kuohais e330802a05 Merge pull request 'finish AHAF #33' (#284) from gsd123/GPUCodeForces:gsd33 into main 2025-12-04 14:54:47 +08:00
Kuohais 9dee0ae00e Merge pull request 'finish Serlu #40' (#291) from gsd123/GPUCodeForces:gsd40 into main 2025-12-04 14:54:38 +08:00
Kuohais 825dce5d8e Merge pull request 'finish FunnelActivationforVisualRecognition #46' (#297) from gsd123/GPUCodeForces:gsd46 into main 2025-12-04 14:54:29 +08:00
Kuohais 84da765424 Merge pull request 'finish ISRLU #49' (#300) from gsd123/GPUCodeForces:gsd49 into main 2025-12-04 14:54:22 +08:00
Kuohais 256be8e13d Merge pull request 'finish PiecewiseLinearUnit #39' (#290) from gsd123/GPUCodeForces:gsd39 into main 2025-12-04 14:54:11 +08:00
Kuohais 7ef720c8bf Merge pull request 'finish cosfaceloss #21' (#317) from hli28146/GPUCodeForces:h21 into main 2025-12-04 14:54:04 +08:00
Kuohais 9b60756910 Merge pull request 'finish Multiquadratic #54' (#305) from gsd123/GPUCodeForces:gsd54 into main 2025-12-04 14:53:50 +08:00
Kuohais a4047f0df6 Merge pull request 'finish FReLU #45' (#296) from gsd123/GPUCodeForces:gsd45 into main 2025-12-04 14:53:38 +08:00
Kuohais 08f94087ae Merge pull request 'finish m-arcsinh #51' (#302) from gsd123/GPUCodeForces:gsd51 into main 2025-12-04 14:53:31 +08:00
Kuohais 0be78409a8 Merge pull request 'finish Colu #34' (#285) from gsd123/GPUCodeForces:gsd34 into main 2025-12-04 14:53:24 +08:00