Commits microsoft/onnxruntime

Move `OrtEp` sanity checks to plugin EP creation and remove check for `OrtEp::ort_version_supported` upper bound (#28601)

edgchen1 committed 171 days ago

Verified 67156b8a

Fix Whisper genai_config context_length using wrong config attribute (#28600)

jiafatom committed 172 days ago

Verified 86aae8c0

QMoE CUDA: Rename build options, refactor PrePack, add GPU kernels (#28583)

tianleiwu committed 172 days ago

Verified ae88f9bc

CPU GroupQueryAttention: Quantized KV Cache with SIMD-optimized MLAS kernels (#28578)

tianleiwu committed 172 days ago

Verified 56640661

Fail loudly when MatMulNBits receives unsupported block_size on CPU EP (#28590)

Copilot committed 172 days ago

Verified 4236d6e9

feat(orttraining): add CPU fallback for FusedAdam optimizer (#28233)

Rishi-Dave committed 172 days ago

Verified 5996a1ec

fix: propagate output_dtype attribute when inserting Q after DQ (#28144)

Rishi-Dave committed 172 days ago

Verified 559162f2

fix: guard ORT_USE_CPUINFO on __linux__ to fix FreeBSD build (#28362)

Rishi-Dave committed 172 days ago

Verified 8d644e5d

Fix EpGraphAssignmentInfo missing issue on nodes assigned to CPU-EP by InsertCastTransformer (#28268)

qti-hungjuiw committed 172 days ago

Verified 856c546c

[CoreML EP] Add Identity, Ceil, Tile builders + drop trivial-only partitions (#28293)

maxwbuckley committed 172 days ago

Verified d0203e1c

Add linux-arm64 binaries to the foundry nuget package (#28579)

baijumeswani committed 172 days ago

Verified bdcd0298

Derive ORT_TEST_VERBOSE from System.Debug via runtime coalesce in plugin test pipelines (#28517)

edgchen1 committed 172 days ago

Verified 13630176

Add quantized KV cache support in CPU GroupQueryAttention (#28576)

tianleiwu committed 173 days ago

Verified 6fbda6d8

add more ORT_ENFORCE when building the tree structure of TreeEnsemble operators (#27677)

xadupre committed 173 days ago

Verified f6e8b0b8

QMoE CUDA EP — FP4/FP8/WFP4AFP8 Quantized Mixture-of-Experts + MoE GEMM Refactor (#28467)

tianleiwu committed 173 days ago

Verified 548ab6e5

[MLAS] Correcting Compilation Errors: onnxruntime/onnxruntime/core/mlas/lib/riscv64/sconv_depthwise_kernel_rvv.cpp:138:18: error: unused variable 'pad_bottom' (#28506)

zejianzhang1982 committed 173 days ago

Verified 3a071a67

Fix Cargo registry auth for network-isolated Linux Python wheel builds (#28556)

kpkbandi committed 173 days ago

Verified a48b4982

Fix protoc error when cross compiling on a linux aarch64 host (#28567)

jocelyn-stericker committed 173 days ago

Verified 192ef6b8

Add EP and hardware device type to Windows ML telemetry (#28477)

angelser committed 173 days ago

Verified 4d1dce86

[MLAS] test: accept canonical NaN in activation NaN round-trip check (#28538)

qiurui144 committed 173 days ago

Verified b38731bf

Validate sparse tensor external file paths (#28408)

adrianlizarraga committed 173 days ago

Verified 6a8f021b

Fix XNNPACK Gemm SIGSEGV on missing and scalar 'C' bias (#28546)

dparikh79 committed 173 days ago

Verified 8c650d81

Fix int32 overflow in CUDA Cast and UnaryElementWise kernels for tensors with >2^31 elements (#28386)

Copilot committed 173 days ago

Verified cd05ef40

[Security] Validate CPU cache_indirection beam indices (#28486)

tianleiwu committed 173 days ago

Verified 2d9f35fc

Skip file path validation in CreateEpContextModel when the output is not a file (#28431)

shiyi9801 committed 174 days ago

Verified ce6aaeec

Add unit test for fix of plugin EP library handle leak in PR 28396 (#28430)

adrianlizarraga committed 174 days ago

Verified 40e30488

Support kquant mixed for whisper export (#28515)

jiafatom committed 174 days ago

Verified d2453bc3

contrib: add mask/input shape consistency checks in MaxpoolWithMask::Compute (#28223)

Copilot committed 174 days ago

Verified 9883e93d

Reject recursive local function definitions during model load (#28187)

tianleiwu committed 174 days ago

Verified 22e537b8

[WebGPU plugin EP] Package improvements (#28525)

edgchen1 committed 174 days ago

Verified 770da7dd