Bump Microsoft.ML.OnnxRuntime.Gpu and Microsoft.ML.OnnxRuntimeGenAI.Cuda - #54
Bump Microsoft.ML.OnnxRuntime.Gpu and Microsoft.ML.OnnxRuntimeGenAI.Cuda#54dependabot[bot] wants to merge 1 commit into
Conversation
dependabot
Bot
added
.NET
|
PR author is in the excluded authors list. |
|
Warning Review limit reached
Next review available in: 33 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
Comment |
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Bumps Microsoft.ML.OnnxRuntime.Gpu from 1.24.4 to 1.28.0 Bumps Microsoft.ML.OnnxRuntimeGenAI.Cuda from 0.13.1 to 0.15.0 --- updated-dependencies: - dependency-name: Microsoft.ML.OnnxRuntime.Gpu dependency-version: 1.28.0 dependency-type: direct:production update-type: version-update:semver-minor - dependency-name: Microsoft.ML.OnnxRuntimeGenAI.Cuda dependency-version: 0.15.0 dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by: dependabot[bot] <support@github.com>
|
Looks like these dependencies are no longer updatable, so this is no longer needed. |
a30040c to
6490efd
Compare
Pinned Microsoft.ML.OnnxRuntime.Gpu at 1.28.0.
Release notes
Sourced from Microsoft.ML.OnnxRuntime.Gpu's releases.
1.28.0
Announcements & Breaking Changes
nvrtcis no longer linked, which significantly reduces the required CUDA redistributable footprint (#29252, #29808, #29705, #29620).OrtModelPackageApinow lives in the experimental C API and may change in future releases (#28746, #29142, #28990).wgsl-genimplementation (#29141, #28355).CUDA_QUANT_PREPROCESSis off by default (#29687).Security Fixes
Memory safety & input validation
bind_inputcausing an out-of-bounds write (#28839)TensorAtfor sub-byte packed types (#28973)Col2Iminputs to prevent heap over-read (#28706)CropAndResizeagainst malformedcrop_sizetensors (#28766)BeamSearchvocab_sizeagainst logits width (#28774)WhisperDecoderSubgraph::CreateInitialFeeds(#29239)SparseAttentionCSR indices/key lengths and rejected zero-dimensionblock_row_indices(#29015, #29242)mask_indexto valid bounds (#29449)MaxpoolWithMaskkernel rank against input spatial rank (#29253)EmbedLayerNorm/SkipLayerNormshapes exceeding 32-bit output indexing (#29264)DecoderAttention/MultiHeadAttentionshape inference and negative-axis handling inExpandDimsshape inference (#29268, #29448)TreeEnsembletarget id validation and added input validation toLinearClassifier(#29293, #29060)DynamicQuantizeLSTMzero-point/scale validation typos (#29462)Loop/Scanoutput concatenation (#29397)raw_datato{0, 1}on unpack (#29238)Resize,PadFusion, and LoRA handling (#28779, #28780, #28801)WithOutputTensorin the Rust bindings (#29251)Integer overflow & allocation size
MlasConvPrepareworking-buffer products andConvTransposepad computation with SafeInt (#29444, #29446)SamplingState::Initthat could cause a heap buffer overflow (#29443)B/scales/zero-points shape inMatMulNBits::PrePack(#29445)ConstantOfShapeoutput size against the input initializer before constant folding (#28751)Pad(int64/int32 truncation),Slice, andGatherBlockQuantized(#28721, #28704, #28718)Supply chain & tooling
... (truncated)
1.27.1
This is a patch release on top of v1.27.0, containing targeted bug fixes, a CUDA QMoE decode-path optimization, and CI/build infrastructure fixes.
Bug Fixes
igemmregression in the KleidiAI path (#28571)Performance
NVIDIA CUDA EP
CI & Build Infrastructure
azcopy(#29274)brew install applesimutilsfailure by trusting the wix/brew tap (#29450)mac-cpu-packing-jobs.yml(#29575)Contributors
Thanks to our 8 contributors for this release!
@tianleiwu, @chilo-ms, @edgchen1, @adrastogi, @damdoo01-arm, @JonathanC-ARM, @martin-klacer-arm, @sanaa-hamel-microsoft
Full Changelog: v1.27.0...v1.27.1
1.27.0
n.b. This release is targeting ONNX 1.21. ONNX 1.22 will be supported in ORT 1.28.
n.b. This changelog was generated via LLM. Only the contributor list has been verified. As always, only trust the commit history.
Announcements & Breaking Changes
Security Fixes
SoftmaxCrossEntropyLossvia label bounds validation (#28004)OneHotinput validation and output-size computation (#28014)Expandand capped constant-folding output sizes (#28055)Tilekernel (#28070)MaxpoolWithMask::Compute(#28223)BitShiftUB for shift amounts greater than or equal to bit width (#28272)seqlens_kvscos_cache) (#28277)WordConvEmbeddingto prevent OOB reads (#28279)CropBasescale handling (#28399)torch.load()calls toweights_only=True(#28421)New Features
Execution Provider Plugin API
OrtEp::OnSessionInitializationEnd()callback (#28319)Core APIs & Runtime
kOrtEpDevice_EpMetadataKey_OSDriverVersionexample and docs (#28282)Quantization & Training Tooling
quantize_static(#28221)ActivationRestrictedAsymmetricquantization option (#28237)... (truncated)
1.26.0
n.b. The following was generated via LLM from Git history. Only the contributor list has been verified.
ONNX Runtime Release 1.26.0
Announcement - Breaking Changes
onnxruntime-<os>-<arch>-gpu_cuda13-<version>.<ext>Highlights
.ortmodel loads (#28164).Security and Reliability Hardening
setattrconfiguration with an allowlist (#28083).CUDA, Attention, and MLAS
WebGPU, WebNN, and JavaScript
... (truncated)
1.25.1
n.b. This changelog is LLM generated. Only the contributor listing has been verified.
ONNX Runtime Release 1.25.1
📢 Announcements & Breaking Changes
ONNX Op Updates
✨ New Features
📊 New ONNX Ops & Model Support
🌐 Web & JavaScript
WebGPU EP
🐛 Bug Fixes
Core Runtime Fixes
SetRawDataInTensorProtoin NVIDIA TensorRT RTX tests (#28065)🙏 Contributors
Thanks to our 7 contributors for this release:
@guschmue, @sanaa-hamel-microsoft, @apsonawane, @eserscor, @ishwar-raut1, @qjia7, @theHamsta
Full Changelog: microsoft/onnxruntime@v1.25.0...v1.25.1
1.25.0
📢 Announcements & Breaking Changes
Build & Platform
Execution Provider Changes
--use_armnnbuild flags and migrate to the MLAS/KleidiAI-backed CPU EP or QNN EP for Qualcomm hardware. (#27447)API Version
🔒 Security Fixes
onnx::TensorProtodata size before allocation (#27547)✨ New Features
🔌 Execution Provider Plugin API & CUDA Plugin EP
... (truncated)
Commits viewable in compare view.
Pinned Microsoft.ML.OnnxRuntimeGenAI.Cuda at 0.15.0.
Release notes
Sourced from Microsoft.ML.OnnxRuntimeGenAI.Cuda's releases.
0.15.0
What's Changed
... (truncated)
0.14.0
What's Changed
... (truncated)
0.13.2
Commits viewable in compare view.