-
Notifications
You must be signed in to change notification settings - Fork 3.8k
Pull requests: microsoft/onnxruntime
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Validate token_id bounds in NGramRepeatBlock to prevent OOB write
#28039
opened Apr 10, 2026 by
vraspar
Contributor
Loading…
FF rel-1.25 to last merge prior to version bump & add first round of cherry picks
#28035
opened Apr 10, 2026 by
sanaa-hamel-microsoft
Contributor
Loading…
fix: idempotent feed setup
release:1.25.0
#28034
opened Apr 10, 2026 by
sanaa-hamel-microsoft
Contributor
Loading…
Add seqlens_k bounds validation in GroupQueryAttention to prevent GEMM OOB
#28031
opened Apr 10, 2026 by
vraspar
Contributor
Loading…
[CUDA EP Plugin] ResourceAcountant integration
#28028
opened Apr 9, 2026 by
yuslepukhin
Member
Loading…
[WebGPU] Fix MHA to ignore past key/value when no present outputs requested
#28027
opened Apr 9, 2026 by
vraspar
Contributor
Loading…
docs: update TensorRT RTX EP documentation for standalone EP ABI and CUDA Graph defaults
#28026
opened Apr 9, 2026 by
ishwar-raut1
Contributor
Loading…
Disable QDQ related transformers for WebNN EP
ep:WebNN
WebNN execution provider
#28020
opened Apr 9, 2026 by
miaobin
Contributor
Loading…
Add CACHE when unsetting CMAKE_CUDA_ARCHITECTURES to ensure it's empty
#28019
opened Apr 9, 2026 by
jmcarcell
Loading…
Use symbol file to export symbols in onnxruntime library on AIX platform as well
#28016
opened Apr 9, 2026 by
ayappanec
Loading…
Fix OneHot depth amplification DoS vulnerability
#28014
opened Apr 8, 2026 by
GopalakrishnanN
Loading…
Bump transformers from 4.50.0 to 5.0.0rc3 in /onnxruntime/python/tools/transformers/models/stable_diffusion/requirements
dependencies
Pull requests that update a dependency file
python
Pull requests that update Python code
#28011
opened Apr 8, 2026 by
dependabot
bot
Loading…
Bump transformers from 4.52.1 to 5.0.0rc3 in /tools/ci_build/requirements/transformers-test
dependencies
Pull requests that update a dependency file
python
Pull requests that update Python code
#28010
opened Apr 8, 2026 by
dependabot
bot
Loading…
Bump transformers from 4.52.1 to 5.0.0rc3 in /onnxruntime/python/tools/transformers/models/llama
dependencies
Pull requests that update a dependency file
python
Pull requests that update Python code
#28009
opened Apr 8, 2026 by
dependabot
bot
Loading…
Bump transformers from 4.52.3 to 5.0.0rc3 in /onnxruntime/python/tools/transformers/models/whisper
dependencies
Pull requests that update a dependency file
python
Pull requests that update Python code
#28008
opened Apr 8, 2026 by
dependabot
bot
Loading…
dml: add per-instance mutexes to fix concurrent session crashes
#28007
opened Apr 8, 2026 by
oysteinkrog
Loading…
Fix OOB reads in SoftmaxCrossEntropyLoss via label bounds validation
#28004
opened Apr 7, 2026 by
vraspar
Contributor
Loading…
fix(ml): use SafeInt checked arithmetic in ML operator coefficient size validation
#28001
opened Apr 7, 2026 by
tianleiwu
Contributor
Loading…
Add DiT attention fusion for F5-TTS and diffusion transformer models
#27999
opened Apr 7, 2026 by
Rishi-Dave
Contributor
Loading…
Add tensor size validation for MatMulBnb4 to prevent OOB read via K/N attribute mismatch
#27995
opened Apr 6, 2026 by
vraspar
Contributor
Loading…
ONNX Attention CUDA: MEA decode, unfused softcap, spec-correct ordering, and NaN fix
#27992
opened Apr 6, 2026 by
titaiwangms
Contributor
Loading…
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.