openvinotoolkit/openvino

[GHA] Switch to 'quiet' mode for gtests and pytests category: CI github_actions

[GPU] Disable oneDNN LSTMSequence category: GPU

Enable default 4bit kv cache category: GPU do not merge

[GPU] Prevent converting MatMul to FC when rank_a less than rank_b category: GPU

CVS-175243 use secondary hf token openvino category: CI github_actions

[GPU] Disable in-place crop when consumer is MVN requiring alignment category: GPU

[GPU] Fix undefined y/x variables in group_normalization_fsv16 fused kernel category: GPU

[GPU][TESTS] Fix race condition in GpuCacheDirWithDotsParamTest category: GPU

[WIP]Fix xattention find_block category: GPU do not merge do_not_review

Bump eslint from 8.57.1 to 10.3.0 in /.github/actions/cache category: CI ExternalPR javascript dependencies

Bump @babel/preset-env from 7.29.2 to 7.29.5 in /.github/actions/cache category: CI ExternalPR javascript dependencies

Bump mistune from 3.2.0 to 3.2.1 in /docs category: docs ExternalPR category: dependency_changes python dependencies

NPUW: Start transitioning on the new serialization format category: NPU category: NPUW

[GPU] MoE 3 GeMM: separate Router Subgraph and MoE body kernels category: GPU category: transformations WIP

[TRANSFORMATIONS] Disable MatMul-Multiply fusion in case of increasing activation values category: transformations priority: high Code Freeze

[GHA][Coverage] coverage_toolkit composite action category: CI do not merge category: dependency_changes do_not_review do_not_merge github_actions no-match-files

[NPUW] Fix GQA broadcast shape to match AttentionBroadcast pattern category: NPU category: NPUW

[GPU] Enable fused MoE for trinity-mini AFMoE (sub-128 group _size + routed_scaling_factor) category: GPU Code Freeze

[Transformations] Simplify MoE router to Transpose + Gather category: IE Tests category: GPU category: transformations

[`NPU`] [`DOCUMENTATION`] [`ENCRYPTION`] Add documentation for `CACHE_ENCRYPTION_CALLBACKS` option category: docs category: NPU

[EXPERIMENT][WIP] [ONNX FE] Add DynamicQuantizeLSTM operator support WIP category: ONNX FE do not merge

[ONNX FE][Transformation] GroupQueryAttention refine work for static shape, make valid kv left aligned [use select with mask] category: transformations do not merge

[Not review]Xiong/block kv integration category: build category: NPU category: NPUW

Make ReduceLogSumExp numerically stable in the ONNX frontend. Fixes overflow to inf for large fp32 inputs. ExternalPR category: ONNX FE

[GPU] integrate onednn gpu - rls-v3.12 category: GPU Code Freeze

[FIX] Recover operation precision with transformation to reduce f16 e… category: GPU category: CPU category: transformations no-match-files

[EISW-204354] Implement changes to enable TSan build with CLang category: build ExternalIntelPR category: dependency_changes

[GPU] New/old shape infer for SDPA aligned category: GPU

Qwen 3.5-3.6 support category: IE Tests category: GPU category: CPU category: transformations WIP

[CORE] Add BevPoolV2 operation category: Core category: IE Tests category: GPU category: build category: transformations category: docs ExternalPR category: ONNX FE category: dependency_changes category: CPP API no-match-files