onnxruntime
Stable Diffusion CUDA Optimizations
#14428
Merged

Stable Diffusion CUDA Optimizations #14428

tianleiwu merged 28 commits into main from tlwu/optimize_sd
tianleiwu
tianleiwu Add benchmark
6d8402ec
tianleiwu Add GroupNorm fusion
0ac952e9
tianleiwu Merge branch 'main' into tlwu/optimize_sd
c1de9fac
tianleiwu [CUDA] Add GroupNormalization operator
29c47dc3
tianleiwu tianleiwu marked this pull request as draft 2 years ago
yuslepukhin
yuslepukhin commented on 2023-01-26
yuslepukhin
yuslepukhin commented on 2023-01-26
yuslepukhin
yuslepukhin commented on 2023-01-26
tianleiwu Add Cast for fp16 group_norm
5f40aa8c
tianleiwu Add SplitGelu fusion
a4c4302d
github-advanced-security
github-advanced-security commented on 2023-01-27
tianleiwu support float type in GroupNorm
f722c5aa
tianleiwu Add SplitGelu operator
4a7bf0d8
tianleiwu format
98b90ca5
tianleiwu format
ea69aec9
tianleiwu misc
9eacd843
tianleiwu update group norm test data to NHWC
c566679a
tianleiwu Fuse Bias and SplitGelu
a9ebeec3
github-advanced-security
github-advanced-security commented on 2023-01-29
tianleiwu update bias split gelu
53a539f1
tianleiwu update GroupNorm doc
a0c4957b
github-advanced-security
github-advanced-security commented on 2023-01-30
tianleiwu tianleiwu force pushed from 66c8992e to d5b9e4d7 2 years ago
tianleiwu packed kv in cross attention
82383dcb
tianleiwu tianleiwu force pushed from d5b9e4d7 to 82383dcb 2 years ago
tianleiwu fix pyright warnings
966b3e72
github-advanced-security
github-advanced-security commented on 2023-01-31
tianleiwu Add unit test of bias split gelu
4a8583e9
tianleiwu fix typo
982663a0
tianleiwu tianleiwu added release:1.14
tianleiwu fix code scanning warnings
73045bbe
tianleiwu fix code scanning warnings
86d57950
tianleiwu address review feedback
efa6d4f4
tianleiwu tianleiwu requested a review from wangyems wangyems 2 years ago
tianleiwu tianleiwu requested a review from yufenglee yufenglee 2 years ago
tianleiwu Add NhwcConv
7a75ce18
tianleiwu fix training api build error
f4d41033
tianleiwu Add float16 test
55a74680
tianleiwu fix type warning
3ff1fe67
tianleiwu update op doc; exclude from hipify
b3a4c014
tianleiwu tianleiwu marked this pull request as ready for review 2 years ago
tianleiwu tianleiwu changed the title [WIP] Stable Diffusion CUDA Optimizations Stable Diffusion CUDA Optimizations 2 years ago
wangyems
wangyems commented on 2023-02-02
wangyems
wangyems dismissed these changes on 2023-02-02
tianleiwu add input checks; clean debug code
1fe78af9
tianleiwu tianleiwu dismissed their stale review via 1fe78af9 2 years ago
yufenglee
yufenglee approved these changes on 2023-02-03
wangyems
wangyems approved these changes on 2023-02-03
tianleiwu tianleiwu merged a6c5ba01 into main 2 years ago
tianleiwu tianleiwu deleted the tlwu/optimize_sd branch 2 years ago
faxu faxu added triage:approved
faxu faxu removed release:1.14

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone