integrate triton into ort #15862
integrate triton
10382c2d
fix compile bug
043b7580
fix softmax select kernel bug
e74cc868
add compile script
26478f25
check metadata file exist
9c8edb1c
add log softmax
d7c9b4b4
fix kernel load multi times bug
a3d7f19b
fix lint
00dc0e54
fix lint
58711a0a
add build config
9f467a5e
fix spelling
88c209fa
add kernel selection
e5020719
fix compile
2c794a5c
add readme
d9f9fab2
add readme
2b04da5a
add triton compiled libs into onnxruntime whl pack
ccb56203
build whl
bc63fd6c
Merge branch 'main' into kailums/triton-dev
18725dee
fix lint
f2634795
fix lint
5106a55c
fix lint
496d6035
integrate triton
8a366520
fix compile bug
e3ff119a
fix softmax select kernel bug
f2620db4
add compile script
fd1cc0a2
check metadata file exist
c64c5079
add log softmax
fb30824b
fix kernel load multi times bug
9edd1118
fix lint
08b6e93f
fix lint
18e86089
add build config
7f78ed4c
fix spelling
1f985cfb
add kernel selection
6f463577
fix compile
0b163c7f
add readme
6a30d4d8
add readme
71288a7e
add triton compiled libs into onnxruntime whl pack
2986cc8f
build whl
fe9acf03
fix lint
093438b8
fix lint
be27feea
fix lint
b9cc24e9
Merge branch 'kailums/triton-dev' of github.com:microsoft/onnxruntime…
20e86faa
combine triton kernel into lib.so
23287697
remove json dependency
b6f99a40
update tutorial
a11dc720
Update ORT_use_trtion_kernel.md
8099be1d
using dlsym to replace depends on Env
8fea69c9
fix missspelling and lint
10081200
Merge branch 'main' into kailums/triton-dev
df0c7948
fix lint
c9e1e27e
fix cuda ci failed
025b7ebd
fix compile bug
a08a4931
fix not support windows dlfcn
91c9ed34
add support for cuda ep
65e904a4
Merge branch 'main' into kailums/triton-dev
b7cb76a1
support cuda and fix symbol bug
0d0e0f22
Merge branch 'main' into kailums/triton-dev
907181ce
kailums
marked this pull request as ready for review 2 years ago
kailums
merged
f62f722c
into main 2 years ago
kailums
deleted the kailums/triton-dev branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub