microsoft/onnxruntime

Pull Requests Commits

Merge main integration through asonawane/ported-ops-hyperconnection-tensor

apsonawane committed 23 days ago

9d0678fb

Merge main integration through asonawane/ported-ops-normalization-rotary

apsonawane committed 23 days ago

8a788aa8

Merge main into normalization and rotary stack

apsonawane committed 23 days ago

26cb2368

Merge updated prerequisite asonawane/ported-ops-hyperconnection-tensor

apsonawane committed 23 days ago

78820657

Merge updated prerequisite asonawane/ported-ops-normalization-rotary

apsonawane committed 23 days ago

6e0540fb

apsonawane committed 23 days ago

c64cce88

apsonawane committed 23 days ago

54870655

apsonawane committed 23 days ago

d76d17c0

Allow onnxruntime_DISABLE_EXCEPTIONS without onnxruntime_MINIMAL_BUILD (#33120)

rvandermeulen committed 23 days ago

Verified 9a662b93

Extend GDN and causal convolution fused state handling

apsonawane committed 23 days ago

62dbc36f

Add fused hyper-connection and tensor CUDA operators

apsonawane committed 23 days ago

437320d9

Add exact normalization and rotary CUDA operator modes

apsonawane committed 23 days ago

77642733

[CUDA] Add opt-in tail-safe INT4 MatMulNBits dispatch for N % 8 == 4, M <= 4 (#33299)

tianleiwu committed 23 days ago

Verified bb68f5de

Skip MatMul BatchNormalization fusion when the channel axis moves (#33392)

samridh10exe committed 23 days ago

Verified dc1ae7a1

[CUDA] Add decode GEMV kernel for K-packed NVFP4 QMoE (#33354)

tianleiwu committed 23 days ago

Verified 69eeb2bb

[CUDA] Add opt-in native E4M3 block-scale conversion to NVFP4 GEMV (#33323)

sayanshaw24 committed 23 days ago

Verified 9eec7d5f

Fix WebGPU Conv2dMM input indexing for vec3 channels (#33432)

gyagp committed 23 days ago

Verified 0614f48d

[WebGPU] Support block-quantized FP8 dense MatMul (#33074)

sayanshaw24 committed 24 days ago

Verified 81f5efab

Revert "Fix non-deterministic constant folding output" (#32471)

xiaofeihan1 committed 24 days ago

Verified c43d712e

Fix safety guards in training loss fusions (#32987)

Yuhx141 committed 24 days ago

Verified c1ea5bff

[CUDA plugin EP] Improve NuGet package metadata (#33405)

tianleiwu committed 24 days ago

Verified ce1d73c2

Fix 1DS telemetry deadlock during Windows process termination (#33291)

qjia7 committed 25 days ago

Verified c64c9fd7

[WebGPU] Extend FP16 MatMul GEMV fast path to M=2–8 (#33351)

aciddelgado committed 26 days ago

Verified b5375da8

[CUDA] Load fpA_intB tactic cache on session create and save on close (#33078)

tianleiwu committed 26 days ago

Verified fed1f4bb

[WebGPU] Add GatedDeltaNetStateReplay contrib operator (#33213)

aciddelgado committed 26 days ago

Verified d8a34452

Zero initialize OrtEpFactory in provider bridge EP factories (#33117)

maxim-davgalev committed 26 days ago

Verified e88538cc

[WebGPU] Upgrade Dawn to the latest version (#33390)

Jiawei-Shao committed 26 days ago

Verified 0767b73d

Fix QLinearSoftmax output for empty inputs (#33401)

DavidLuong98 committed 26 days ago

Verified 454b3dd7

Bump github/issue-labeler from 3.4 to 3.5 (#33388)

dependabot[bot] committed 26 days ago

Verified 0fb935a1

[docs] Experimental C API usage (#29701)

edgchen1 committed 26 days ago

Verified 529efb6d

Older