[ORT 1.17.0 Release] Cherry pick 1st round #19243
YUNQIUGUO
merged
23 commits into
rel-1.17.0
from
yguo/cherry-pick-1st-round
more inputs support for LLM exporter (#19005)
357d3850
Fix untyped float values in quantization tool missing from PR #18043 …
c1760bfe
[js/web] allow proxy to load model with 1GB <= size < 2GB (#19178)
de93132e
[js/web] show warning when numThreads is set but threads is not suppo…
89dae2d6
Check the ep_cache_context and don't allow access outside the directo…
eb77b5b7
Update x64 template kernel library for 'sqnbitgemm' (#19016)
3d06a91f
[js/web] upgrade dependency packages version (#19193)
2b865157
Update LLaMA attention fusions (#19200)
5eebd09d
Fix issue that the generated context cache model inputs/outputs order…
3c2065c2
[TensorRT EP] Enhance EP context configs in session options and provi…
9b304859
phi2 contrib ops changes (#19112)
f9ad1770
[QNN EP] Expose device-level session options (#19212)
6aa7f796
[aarch64] Add Sbgemm kernel to accelerate fp32 tensor matmul with bfl…
041dfd59
[QNN EP] Create Windows ARM64 nightly python package (#19128)
95a746fa
unet fusion for stable diffusion webui (#19227)
c1def2e7
Modified the condition to load the optimiser model (#18891)
3c6adf3e
Fix Fuzz Testing CI (#19228)
d9688112
yufenglee
dismissed these changes
on 2024-01-23
kunal-vaishnavi
dismissed these changes
on 2024-01-23
yf711
dismissed these changes
on 2024-01-23
adrianlizarraga
dismissed these changes
on 2024-01-23
baijumeswani
dismissed these changes
on 2024-01-23
snnn
dismissed these changes
on 2024-01-23
tianleiwu
dismissed these changes
on 2024-01-23
wejoncy
dismissed these changes
on 2024-01-24
fs-eire
dismissed these changes
on 2024-01-24
Fix AMD pipeline test failures (#19250)
8bdea53e
wangyems
dismissed these changes
on 2024-01-24
xadupre
dismissed these changes
on 2024-01-24
tianleiwu
dismissed these changes
on 2024-01-24
remove old quantization tool file (#19247)
0714f0c4
[TensorRT EP] Avoid calling unavailable function with cpu python pack…
aaa577d1
[TensorRT EP] Fix mem leak for TRT plugins custom ops (#19248)
7d941f4a
Remove USE_CUTLASS flag (#19271)
5bb85b69
Update abseil to a release tag and register neural_speed (#19255)
099cefb5
snnn
approved these changes
on 2024-01-26
pranavsharma
approved these changes
on 2024-01-26
yufenglee
approved these changes
on 2024-01-26
adrianlizarraga
approved these changes
on 2024-01-26
yf711
approved these changes
on 2024-01-26
tianleiwu
approved these changes
on 2024-01-26
kunal-vaishnavi
approved these changes
on 2024-01-26
baijumeswani
approved these changes
on 2024-01-26
wangyems
approved these changes
on 2024-01-27
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub