openvinotoolkit/openvino

[GPU] fix dGPU func testcases in smoke_ScaledAttnDynamic4D_GPU and smoke_MatMulCompressedWeights_extra_multiply category: GPU

[AUTO] Enable telemetry via IPF for device selection logic category: inference category: Core category: IE Tests category: build category: Python API category: samples category: docs do not merge category: AUTO do_not_review category: CPP API category: docs_snippets

Bugfix/floor category: GPU category: CPU

[CPU] Add ASCII diagram for MemoryInput/MemoryOutput memory mapping and reuse category: CPU ExternalPR

[NPUW] Add Mixture of Experts support to model builder category: NPU category: NPUW

[WIP][MLIR][GPU] MLIR feature development (CI only) category: inference category: Core category: GPU category: build category: transformations category: docs ExternalIntelPR category: dependency_changes no-match-files category: NPU

Extend moe_3gemm to all Ultra series iGPU category: GPU under_perf_check

[NPU] Fix coverity issues category: NPU

Bump @actions/core from 1.11.1 to 3.0.0 in /.github/actions/wait-for-check-completion category: CI ExternalPR javascript dependencies

Bump @actions/core from 1.11.1 to 3.0.0 in /.github/actions/cache category: CI ExternalPR javascript dependencies

Bump eslint-plugin-github from 4.10.2 to 6.0.0 in /.github/actions/cache category: CI ExternalPR javascript dependencies

Bump paddlepaddle from 3.0.0 to 3.3.1 in /src/bindings/python category: Python API ExternalPR category: dependency_changes python dependencies

Bump prettier from 3.5.3 to 3.8.2 in /.github/actions/cache category: CI ExternalPR javascript dependencies

Bump babel-preset-jest from 29.6.3 to 30.3.0 in /.github/actions/cache category: CI ExternalPR javascript dependencies

Update keras requirement from <=3.13.2 to <=3.14.0 in /tests ExternalPR category: dependency_changes python dependencies

[NPU] Un-skip DX12RemoteRunTests func tests category: NPU

[Core] Test core.read_model(wchar path with unicode) category: inference

[GPU] Optimize ArgMaxMin buffer allocation for TopK=1 category: GPU ExternalIntelPR

Skip StatefulSDPAFusion for models with shared KV-cache category: CPU

feat: Add Copilot agent instructions (migrated from MEAT) category: docs no-match-files

[NPUW] Detect asymmetric cross-group connections to disable F16IC. category: NPU category: NPUW

[GPU] add xe2/xe3 GOPS fallback when device_ops_table misses category: GPU

Bump pytest from 9.0.2 to 9.0.3 in /tests/e2e_tests ExternalPR category: dependency_changes python dependencies

Use gather matmul in gpu pipeline category: GPU category: transformations

[DO NOT MERGE] CVS-175243 use-the-hf-token test-rate-limit-api category: CI category: docs category: TF FE github_actions category: PyTorch FE category: JAX FE

[NPUW] Model builder: add linear attention hybrid architecture support category: NPU category: NPUW

[Bug]: OpenVINO Backend is not support bfloat16 fully in Python Binding category: Python API ExternalPR

[GPU] Enable dynamic quantization for MXFP8 & regular FP8 dtypes category: Core category: GPU category: transformations category: LP transformations

[PT FE] Implement patch for quantized models in torch.export path category: Python API category: PyTorch FE category: OVC

[CPU][ARM] Support Convolution int8 mixed precision category: CPU