Repository navigation
Releases
Releases Β· openvinotoolkit/openvino.genai
2026.4.1.0
What's Changed
Full Changelog: 2026.4.0.0...2026.4.1.0
2026.4.0.0
What's Changed
- Bump product version 2026.4.0 by @jkoniusz in #4125
- Bump @types/node from 24.13.2 to 24.13.3 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #4107
- Xfail LLM NPU test failing in precommits by @as-suvorov in #4122
- Bump cmake 3.26 by @as-suvorov in #4124
- Add
EmbeddingPipelineclass for Qwen3-VL-Embedding by @pavel-esir in #4093 - Fix coverity 2026.3 by @as-suvorov in #4119
- Align
token_type_idsinput with PA op spec by @as-suvorov in #4110 - Add resize image for VLM benchmarking by @JohnLeFeng in #3725
- Update LLM benchmark sample by @JohnLeFeng in #4074
- Bump the npm-dependencies group across 1 directory with 2 updates by @dependabot[bot] in #4142
- Bump the pip-dependencies group across 5 directories with 3 updates by @dependabot[bot] in #4144
- Restore Python < 3.11 compatibility for av by @skuros in #4129
- Cache Minja Template by @apaniukov in #4148
- [VLM] QWEN-3-Omni support by @sgonorov in #4102
- Bump the github-actions group across 1 directory with 4 updates by @dependabot[bot] in #4154
- Bump typescript-eslint from 8.63.0 to 8.64.0 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #4153
- Fix missing Abseil symbols on Android after OpenVINO Protobuf update by @bumbosiepsak in #4163
- [Gemma3] Enable PA, fix prompt normalization, unskip tests by @yatarkan in #4167
- Adjust KV cache capacity calculation with NPUW plugin by @AlexanderKalistratov in #4136
- [Whisper]: Split on unicode non whitespace languages by @as-suvorov in #4131
- [WWB] Add patch for speechbrain 1.1.0 import by @avasenin-14 in #4151
- Bump the github-actions group with 2 updates by @dependabot[bot] in #4171
- Enable Gemma4 video input by @yatarkan in #4114
- [wwb] Fix wrong output in case of results have different amount of lines by @sbalandi in #4178
- [GenAI tools] Update codeownwer by @sbalandi in #4179
- Bump the pip-dependencies group across 3 directories with 3 updates by @dependabot[bot] in #4183
- Fix imagine size config on text-to-image model test by @DingZhangIntel in #4155
- [Docs] Enable redirect plugin, rename & align VLM page title and URLs by @yatarkan in #4173
- [wwb] Add support of visual embeddings model by @sbalandi in #4135
- Import blob from ov.Tensor for SDXL on text-to-image pipeline by @JohnLeFeng in #3874
- Fix undefined symbol for format in libopenvino_genai.so by @jwludzik in #4160
- Bump the github-actions group across 1 directory with 4 updates by @dependabot[bot] in #4192
- [llm_bench] Add text generation chat pipeline by @sbalandi in #4048
- Expose VLM request-level metrics via GenerationHandle by @junruizh2021 in #3860
- Bump brace-expansion from 1.1.14 to 1.1.16 in /src/js by @dependabot[bot] in #4195
- Bump the pip-dependencies group across 3 directories with 2 updates by @dependabot[bot] in #4193
- Update docs with ASRPipeline by @as-suvorov in #4128
- Bump fast-uri from 3.1.2 to 3.1.4 in /site by @dependabot[bot] in #4197
- Bump body-parser from 1.20.5 to 1.20.6 in /site by @dependabot[bot] in #4198
- Bump shell-quote from 1.8.4 to 1.10.0 in /site by @dependabot[bot] in #4199
- Bump svgo from 3.3.3 to 3.3.4 in /site by @dependabot[bot] in #4201
- enabled new properties for tokenizer and detokenizer by @dtrawins in #3832
- [CI] [GHA] Use official
actions/download-artifactaction by @akashchi in #4203 - Remove smart-ci deps wa by @as-suvorov in #4204
- [VideoGeneration][Text2Video] LTX set_timesteps fix, disable TaylorSeerCache by @likholat in #4172
- [CI] [GHA] [AW] Introduce PR failure investigator by @akashchi in #4194
- Enable DFlash with support of Qwen3.6 by @ofirzaf in #3938
- Fix double video frames sampling for Qwen3-VL and Qwen3-Omni by @yatarkan in #4206
- [wwb] Bump transformers version to <=5.13 by @avasenin-14 in #4115
- Bump typescript-eslint from 8.64.0 to 8.65.0 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #4191
- [wwb] Update support for gemma3n by @sbalandi in #4208
- Update .github/copilot-instructions.md by @Wovchena in #4214
- Update .github/pull_request_template.md by @Wovchena in #4215
- [llm_bench] Fix KeyError: 'chat_idx' for text_embed/text_rerank CSV report by @dylanneve1 in #4212
- [tools] Add avasenin to codeowners by @avasenin-14 in #4217
- Extend guidelines and review items in .github/copilot-instructions.md by @Wovchena in #4216
- PNDM scheduler fix by @likholat in #4157
- [VLM] Force FP32 only for Qwen3-Omni CodePredictor by @byungilm in #4187
- [wwb] Add suport for Qwen-Omni-MoE by @avasenin-14 in #4015
- Add docs for Semantic Search using
EmbeddingPipelineby @pavel-esir in #4174 - [WWB] Split 43 minute tests suite by @avasenin-14 in #4175
- [genai] Optimize Qwen_omni to enable VLSDPA and gpu offloading of image pre-processing by @byungilm in #4018
- Bump the pip-dependencies group across 1 directory with 2 updates by @dependabot[bot] in #4229
- Use single tokenizer for VLM CB backend. Gemma4-12b-it template fix by @as-suvorov in #4213
- Bump yargs from 18.0.0 to 18.1.0 in /samples/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #4228
- [WWB] Bump torch to 2.13.0 by @avasenin-14 in #4233
- Bump the github-actions group across 1 directory with 5 updates by @dependabot[bot] in #4235
- Bump the pip-dependencies group across 3 directories with 3 updates by @dependabot[bot] in #4236
- Bump postcss from 8.5.14 to 8.5.23 in /site by @dependabot[bot] in #4224
- [skills] update genai skills by @Mohamed-Ashraf273 in #4066
- Bump the pip-dependencies group across 4 directories with 3 updates by @dependabot[bot] in #4239
- Add QWen3.5 to visual_text_gen by @gitpqLee in #4232
- [llm_bench] Add support of Qwen3 ASR by @avasenin-14 in #4231
- [CVS-191448][Qwen3-reranker] The query and doc need to apply template before feeding into qwen3 reranker model by @bopeng1234 in #4219
- [Docs] Add Speculative Decoding page...
2026.3.0.0
What's Changed
- Bump product version 2026.3.0 by @akladiev in #3858
- [wwb] Update video inputs to avoid big video by @sbalandi in #3777
- Bump the npm-dependencies group across 1 directory with 2 updates by @dependabot[bot] in #3849
- Bump typescript-eslint from 8.59.2 to 8.59.3 in /site in the npm-dependencies group across 1 directory by @dependabot[bot] in #3850
- skip test_qwen3_embedding_npu tests by @as-suvorov in #3859
- [samples] Move encrypted_model_vlm from minicpmv to qwen3 by @sbalandi in #3842
- Bump the pip-dependencies group across 5 directories with 6 updates by @dependabot[bot] in #3824
- [llm_becn/wwb] Update torch/torchvision version range by @sbalandi in #3863
- Don't require ABI stability by @Wovchena in #3861
- Fix Gemma3 chat template formatting by @yatarkan in #3867
- [C API] ChatHistory support in VLM pipeline by @zhaohb in #3631
- Bump openvinotoolkit/openvino from 7f61dc3cf40c03638386397c6f8f98bf23f25a00 to 48b684f1ba3a01e573b3de6444e9e37756e3cdc9 in the github-actions group across 1 directory by @dependabot[bot] in #3851
- Bump the pip-dependencies group across 5 directories with 7 updates by @dependabot[bot] in #3869
- Bump the pip-dependencies group across 3 directories with 2 updates by @dependabot[bot] in #3878
- Bump brace-expansion from 5.0.5 to 5.0.6 in /.github/actions/install_wheel by @dependabot[bot] in #3880
- Bump openvinotoolkit/openvino from 48b684f1ba3a01e573b3de6444e9e37756e3cdc9 to 5db1bfbd991e4f604111d9c69b0007f5a2f8f87c in the github-actions group by @dependabot[bot] in #3877
- Bump webpack-dev-server from 5.2.3 to 5.2.4 in /site by @dependabot[bot] in #3882
- [JS] Add VLMPipeline samples by @Retribution98 in #3287
- Bump typescript-eslint from 8.59.3 to 8.59.4 in /site in the npm-dependencies group across 1 directory by @dependabot[bot] in #3884
- [JS] Fix CI fails by @Retribution98 in #3879
- Bump the pip-dependencies group across 2 directories with 1 update by @dependabot[bot] in #3886
- Bump typescript-eslint from 8.59.3 to 8.59.4 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #3883
- Bump the github-actions group with 2 updates by @dependabot[bot] in #3885
- Deprecated
start_chat()/finish_chat()API in VLM and CB pipelines by @yatarkan in #3889 - [Docs] Fix build by @yatarkan in #3891
- Kokoro Text-to-Speech Support by @RyanMetcalfeInt8 in #3483
- [WWB] Create gt and output folders if they don't exist by @CuriousPanCake in #3890
- Decrease GGUF timeouts by @Wovchena in #3894
- Bump optimum-intel to May 20 (140e49a6) for all tests by @peterchen-intel in #3852
- Remove deprecation prints from C++ by @yatarkan in #3899
- Add denoising_process C++ and Python samples by @byekrang in #3881
- Skip Mac GGUF tests by @Wovchena in #3902
- [SD] Dynamic Tree Search Sampler for draft generation and main validation by @GuoliangShiIntel in #3451
- Bump the github-actions group across 1 directory with 3 updates by @dependabot[bot] in #3892
- Bump langchain-community from 0.4.1 to 0.4.2 in /tests/python_tests in the pip-dependencies group across 1 directory by @dependabot[bot] in #3908
- Bump typescript-eslint from 8.59.4 to 8.60.0 in /site in the npm-dependencies group across 1 directory by @dependabot[bot] in #3912
- [WWB] Skip prompt with incoherent answer for Qwen3.5-0.8B by @yatarkan in #3898
- Bump typescript-eslint from 8.59.4 to 8.60.0 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #3910
- Bump the github-actions group across 1 directory with 2 updates by @dependabot[bot] in #3913
- Bump eslint-plugin-prettier from 5.5.5 to 5.5.6 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #3918
- [llm_bench] Add per-stage performance metrics for WhisperPipeline and sampling duration for LLMPipeline by @goyaladitya05 in #3669
- Bump openvinotoolkit/openvino from 51b2fef55c075a40ad3a5e84dea1ffbf68f88b5f to ac001bacd3a9f207db30326a605154e14783b40a in the github-actions group by @dependabot[bot] in #3919
- Bump typescript-eslint from 8.60.0 to 8.60.1 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #3924
- Added dense LFM2 class to text_gen type by @AsyaPronina in #3929
- Bump the npm-dependencies group across 1 directory with 4 updates by @dependabot[bot] in #3926
- Fix embedding start time for VLM pipeline on NPU by @JohnLeFeng in #3771
- Replace
skipif()back withxfail()by @Wovchena in #3905 - [wwb] make long prompt by default by @sbalandi in #3903
- [CI] Skip Kokoro and Gemma3 (PA) failing tests by @yatarkan in #3945
- Bump the github-actions group across 1 directory with 2 updates by @dependabot[bot] in #3925
- Bump the npm-dependencies group across 1 directory with 2 updates by @dependabot[bot] in #3952
- Bump the pip-dependencies group across 3 directories with 6 updates by @dependabot[bot] in #3949
- Bump typescript-eslint from 8.60.1 to 8.61.0 in /site in the npm-dependencies group across 1 directory by @dependabot[bot] in #3953
- [wwb/llm_bench] Add skills for fail analysis by @sbalandi in #3896
- [CI] [GHA] Use
ninjaas a generator for wheel build on mac by @akashchi in #3928 - [wwb, llm_bench] Move to dtype auto for pt models by @sbalandi in #3793
- ignore cache_interval_multiplier for non LM models by @dtrawins in #3943
- MODEL_PROPERTIES support for all VLM model roles by @dkalinowski in #3781
- wwb: Add support for Kokoro by @RyanMetcalfeInt8 in #3897
- add truncation
genai::Tokenizer::encodeby @pavel-esir in #3876 - Bump shell-quote from 1.8.3 to 1.8.4 in /site by @dependabot[bot] in #3959
- Bump @types/node from 24.13.1 to 24.13.2 in /src/js in the npm-dependencies group across 1 directory by @dependabot[bot] in #3969
- Bump the github-actions group across 1 directory with 2 updates by @dependabot[bot] in #3970
- Add LFM2(.5) and Qwen3Next to the Docs by @apaniukov in #3972
- Kokoro tts test fix by @RyanMetcalfeInt8 in #3961
- Bump the pip-dependencies group across 2 directories with 3 updates by @dependabot[bot] in #3971
- [CMAKE] Add pdb install by @mryzhov in #3973
- Fix StaticWhisperPipeline to work with transformers v5 by @eshiryae in #3923
- Bump the github-actions group with 2 updates by @dependabot[bot] in https://github.com/ope...
2026.2.1.0
What's Changed
Full Changelog: 2026.2.0.0...2026.2.1.0
2026.2.0.0
What's Changed
- Bump tqdm from 4.67.1 to 4.67.3 in /tools/who_what_benchmark by @dependabot[bot] in #3510
- Bump product version to 2026.2.0 by @akladiev in #3521
- Use snapshot_download for datasets in whisper tests by @as-suvorov in #3421
- ci-doctor agentic workflow: extend tools, add logs download step by @as-suvorov in #3504
- Bump langchain-core from 1.2.19 to 1.2.20 in /tests/python_tests by @dependabot[bot] in #3526
- Update copyright to 2026 for remain files by @JohnLeFeng in #3455
- Update accelerate requirement from <=1.12.0,>=0.26.0 to >=0.26.0,<=1.13.0 in /tools/who_what_benchmark by @dependabot[bot] in #3511
- [wwb] Move to transformers 5 by @sbalandi in #3441
- [wwb] Add custom processor for qwen3_vl by @sbalandi in #3487
- Bump the npm_and_yarn group across 2 directories with 1 update by @dependabot[bot] in #3532
- fix: Request for spelling correction (consamption -> consumption). by @JiwaniZakir in #3506
- Update datasets requirement from <=4.7.0,>=3.6.0 to >=3.6.0,<=4.8.3 in /tools/who_what_benchmark by @dependabot[bot] in #3538
- [Video Generation] Add LoRA adapter support for Text2VideoPipeline (Supersedes #3309) by @goyaladitya05 in #3362
- Add guidance rescale [Divide by 0 check added] by @Yash-Vijay29 in #3369
- Update imageio[pyav] requirement from <=2.37.2 to <=2.37.3 in /tools/who_what_benchmark by @dependabot[bot] in #3548
- Update datasets requirement from <=4.8.3,>=3.6.0 to >=3.6.0,<=4.8.4 in /tools/who_what_benchmark by @dependabot[bot] in #3562
- [llm_bench] [wwb] Update torch related deps by @wkobielx in #3564
- Bump sentence-transformers from 5.2.2 to 5.3.0 in /tools/who_what_benchmark by @dependabot[bot] in #3527
- [wwb] Add text generation in chat mode by @sbalandi in #3472
- Fix dependabot alert in docs dependencies by @yatarkan in #3450
- Update cmake requirement from ~=3.23.0 to ~=4.3.0 by @dependabot[bot] in #3556
- Bump torchvision from 0.17.2 to 0.26.0+cpu in /samples by @dependabot[bot] in #3558
- Add pre-commit setup instructions to CONTRIBUTING.md by @goyaladitya05 in #3569
- Add check-json pre-commit hook by @goyaladitya05 in #3536
- Bump timm from 1.0.25 to 1.0.26 by @dependabot[bot] in #3576
- [wwb][llm_bench] Bump torchcodec to align new torch by @sbalandi in #3581
- Bump the npm_and_yarn group across 2 directories with 1 update by @dependabot[bot] in #3574
- Update timm requirement from <=1.0.25 to <=1.0.26 in /tools/llm_bench by @dependabot[bot] in #3580
- [wwb] Add chat mode for VLM by @sbalandi in #3485
- kczarnec-memory-monitor-in-process by @krzyczar in #3382
- [llm_bench] Avoid run pipeline on optimum if genai was required by @sbalandi in #3486
- Bump diffusers from 0.37.0 to 0.37.1 by @dependabot[bot] in #3577
- [Stale PRs]: Increase operations per run by @as-suvorov in #3595
- Bump diffusers to 37.1 by @as-suvorov in #3602
- Bump json5 from 0.13.0 to 0.14.0 by @dependabot[bot] in #3603
- [ci-doctor]: Checkout pr commit with manual trigger by @as-suvorov in #3606
- Cross validate tools and GenAI dependencies by @as-suvorov in #3596
- Bump the npm_and_yarn group across 2 directories with 2 updates by @dependabot[bot] in #3589
- Support Linear State in SDPA Pipeline by @apaniukov in #3359
- Split VLM & LLM tests to separated scopes by @olpipi in #3553
- Fix typo in text_generation sample README by @FarseenSh in #3607
- Fix typos and docs issues across multiple sample READMEs by @FarseenSh in #3615
- [ci-doctor]: Fix repo checkout by @as-suvorov in #3621
- [Agentic Skills]: Update documentation skill by @as-suvorov in #3552
- Timestamps closer to model.generate() in text_generation by @kmurczki in #3614
- [Agentic Skills]: Add model checker skill by @as-suvorov in #3550
- [wwb] Enable WWB to run LoRA adapter evaluation support for Text2VideoPipeline by @goyaladitya05 in #3546
- Update brace-expansion to fix CVE-2026-33750 by @mlukasze in #3635
- [GENAI]Introduce add_extension to genai. by @xipingyan in #2952
- Bump the npm_and_yarn group across 1 directory with 2 updates by @dependabot[bot] in #3637
- [Doc] Extensions property document by @sunxiaoxia2022 in #3547
- Fix CDPruner SIMD regression: replace compile-time AVX2 flags with runtime AVX detection by @yangwang201911 in #3601
- Fix Windows separator by @Wovchena in #3652
- Extend copilot instructions.md by @Wovchena in #3654
- Update ci-doctor manual dispatch instructions by @as-suvorov in #3658
- Remove
github.event_namefrom ci-doctor instruction by @as-suvorov in #3659 - [llm_bench] Define use_case as default when model_type unknown and task is set by @sbalandi in #3646
- [Image generation pipeline] Add
m_is_blobflag to handle infer request when import the blob to NPU by @JohnLeFeng in #3555 - [JS] Use std::filesystem::path instead of strings by @Retribution98 in #3598
- [JS] Implement Text2SpeechPipeline by @Retribution98 in #3519
- Update python requests, langchain-core, torchvision, torchaudio deps by @as-suvorov in #3656
- Multinomial sampling rework by @mzegla in #3634
- Bump pillow from 12.1.1 to 12.2.0 in /tools/llm_bench by @dependabot[bot] in #3666
- Enable LTO on GenAI Obj by @apaniukov in #3672
- [llm_bench] Align behavior for long prompt for reranking pipeline by @sbalandi in #3674
- Ignore smart-ci dependency by dependabot by @as-suvorov in #3684
- Enable HunYuan (tencent/HY-MT1.5-1.8B) model support by @as-suvorov in #3682
- Refactor: extract duplicated make_tensor_slice into shared utils by @FarseenSh in #3616
- Fix init_attention_mask to always allocate i64 tensor by @FarseenSh in #3610
- Ignore openvinotoolkit/openvino gha updates by @as-suvorov in #3693
- Enable TaylorSeer caching by default for LTXVideo by @l-bat in #3642
- [Dependabot]: ignore actions/checkout by @as-suvorov in #3697
- [agents]: Use gpt-5-mini for ci-doctor by @as-suvorov in #3685
- Bump the github-actions group across 1 directory with 10 updates by @dependabot[bot] in #3700
- Fix grammar and typos across sam...
2026.1.0.0
What's Changed
- Skip nodejs tests on mac by @as-suvorov in #3227
- Bump json5 from 0.12.1 to 0.13.0 by @dependabot[bot] in #3169
- Bump product version 2026.1.0 by @akladiev in #3234
- [NPU] Support NPUW for text-embedding models by @mengweiguo in #3088
- Implement Adaptive R-KV mode for cache eviction by @vshampor in #2762
- Bump einops from 0.8.1 to 0.8.2 in /tests/python_tests by @dependabot[bot] in #3240
- Bump einops from 0.8.1 to 0.8.2 in /samples by @dependabot[bot] in #3237
- [CI] WWB and LLM Bench for Video Generation CI by @sgonorov in #3228
- [Coverity]: Word level timestamps dtw overflow by @as-suvorov in #3241
- [wwb] Update requirements for miniCPM-o by @sbalandi in #3230
- Text2Video sample fix by @sgonorov in #3243
- Bump xgrammar version by @pavel-esir in #3221
- Add close stale PR workflow by @as-suvorov in #3229
- Enable mark and close stale PRs workflow by @as-suvorov in #3247
- Skip NPU cache dir tests for LLM pipeline by @as-suvorov in #3251
- Bump peft from 0.17.1 to 0.18.1 in /samples by @dependabot[bot] in #3238
- Bump peft from 0.17.1 to 0.18.1 in /tests/python_tests by @dependabot[bot] in #3239
- Add copilot_instructions.md by @as-suvorov in #3246
- [VLM][NPU] Enable F16IC for gemma3 by @AlexanderKalistratov in #3256
- Bump timm from 1.0.22 to 1.0.24 by @dependabot[bot] in #3262
- Fix coverity issues by @sgonorov in #3252
- Bump opencv-python from 4.12.0.88 to 4.13.0.90 by @dependabot[bot] in #3261
- Bump timm from 1.0.22 to 1.0.24 in /tests/python_tests by @dependabot[bot] in #3265
- [JS] Refactor LLMPipeline by @Retribution98 in #3206
- [Docs]: Add whisper word level timestamps by @as-suvorov in #3231
- [WWB] Increased the number of long-prompt samples by @l-bat in #3266
- Update codeowners by @as-suvorov in #3268
- Bump pillow from 12.0.0 to 12.1.0 in /samples by @dependabot[bot] in #3275
- [DOCS] LTX Video Generation Docs by @likholat in #3232
- Extend .github/copilot-instructions.md by @Wovchena in #3281
- Update pull_request_template.md by @MaximProshin in #3271
- Bump diffusers from 0.35.2 to 0.36.0 by @dependabot[bot] in #3140
- [wwb] Avoid install auto-gptq/autoawq by @sbalandi in #3242
- Added GGUF format support for LoRA adapters by @goyaladitya05 in #3204
- Extend copilot-instructions.md by @Wovchena in #3285
- Bump @isaacs/brace-expansion from 5.0.0 to 5.0.1 in /.github/actions/install_wheel in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3279
- Bump opencv-python from 4.13.0.90 to 4.13.0.92 in /samples by @dependabot[bot] in #3289
- Bump vector-quantize-pytorch from 1.27.15 to 1.27.20 in /tests/python_tests by @dependabot[bot] in #3283
- [wwb] Update reranker/embedder tests by @sbalandi in #2983
- Revert rope shape and If input type changes from PR 3124 (target 2026/1) by @mitruska in #3248
- [Doc] Visual Token Pruning by @peterchen-intel in #2861
- Make Tensor data access const-correct by @sgonorov in #3291
- [NPUW][VLM][AUTO] Using Auto plugin for VLMs embeddings when running on NPU by @AlexanderKalistratov in #3220
- Unskip NPU cache_dir tests by @as-suvorov in #3292
- Bump langchain-core from 1.2.5 to 1.2.9 in /tests/python_tests by @dependabot[bot] in #3297
- Lint: whitespaces and newlines rules applied by @as-suvorov in #3295
- CVS-178941: Align VLM resize pre-processing with optimum by @RyanMetcalfeInt8 in #3172
- Switch tests from 8 cores 64 GB RAM Linux runner to 32 GB by @ababushk in #3099
- Fix Text2VideoPipeline crash with guidance_scale by @sgonorov in #3270
- Bump webpack from 5.98.0 to 5.105.0 in /site in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3302
- kczarnec-add-metrics-to-memory-monitor by @krzyczar in #3164
- [wwb] Fix num_inference_steps for inpainting and im2im by @sbalandi in #3299
- [Whisper]: Fix word timestasmps processing perf metrics by @as-suvorov in #3294
- Deprecate
start_chat()/finish_chat()API in LLM pipeline, update samples by @yatarkan in #3217 - [JS] Refactor tests by @Retribution98 in #3245
- Update Tokenizers by @apaniukov in #3311
- [wwb] Update model and add metrics for video generation simularity by @sbalandi in #3286
- [wwb] Fix progress bars by @sbalandi in #3319
- Bump langchain-core from 1.2.9 to 1.2.11 in /tests/python_tests by @dependabot[bot] in #3325
- Make link visible by @Wovchena in #3333
- Extend copilot-instructions.md by @Wovchena in #3332
- Bump pillow from 12.1.0 to 12.1.1 by @dependabot[bot] in #3323
- Bump qs from 6.14.1 to 6.14.2 in /site in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3342
- Fix load_dataset fails by @as-suvorov in #3345
- [llm_bench] Add class for lfm2-moe by @sbalandi in #3357
- [wwb] Fix Qwen3-Reranker-0.6B-seq-cls with GenAI low similarity by @sbalandi in #3341
- Kczarnec small fixes in memory monitor by @krzyczar in #3356
- Fix OpenVINO version by @as-suvorov in #3358
- Bump minimatch from 10.1.1 to 10.2.1 in /.github/actions/install_wheel in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3360
- Update LongBench tests by @l-bat in #3351
- [wwb][llm-bench] Fix version of required dependency in requirements.txt by @sbalandi in #3314
- Fix Text2VideoPipeline crash with guidance_scale=1 when using default constructor by @sgonorov in #3316
- Remove flux-1-dev-non-commercial-license by @Wovchena in #3350
- Bump bitsandbytes from 0.49.1 to 0.49.2 in /tools/llm_bench by @dependabot[bot] in #3374
- Update scipy requirement from <=1.17.0,>=1.3.2 to >=1.3.2,<=1.17.1 in /tools/who_what_benchmark by @dependabot[bot] in #3375
- Bump ajv from 6.12.6 to 6.14.0 in /.github/actions/install_wheel in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3370
- Extend copilot-instructions.md by @Wovchena in #3377
- Use OV latest_available_commit...
2026.0.0.0
What's Changed
- Add CONTRIBUTING.md by @Wovchena in #2903
- [JS] Support ChatHistory in .generate() by @Retribution98 in #2896
- Bump product version 2026.0 by @akladiev in #2970
- Support QWen VL video inputs by @xipingyan in #2514
- Correct usage of ov::Tensor::data for 26.0 release by @praasz in #2934
- [WWB] Apply qwen3 rerank template for GenAI pipeline by @as-suvorov in #2969
- Bump pydantic from 2.12.3 to 2.12.4 in /samples by @dependabot[bot] in #2974
- Bump timm from 1.0.21 to 1.0.22 in /tests/python_tests by @dependabot[bot] in #2965
- Bump timm from 1.0.21 to 1.0.22 in /samples by @dependabot[bot] in #2967
- Bump langchain-core from 1.0.1 to 1.0.3 in /tests/python_tests by @dependabot[bot] in #2960
- Update use tensor data member by @praasz in #2978
- Update condition for enum value conflicting with windows headers by @yatarkan in #2979
- [Docs] Add Structured Output Docs by @apaniukov in #2950
- [JS] Fix structured output test by @Retribution98 in #2951
- [Docs] Remove LoRA column for not supported use cases, remove duplicated documents & assets by @yatarkan in #2981
- [WWB] Add eagle3 pipeline by @sunxiaoxia2022 in #2812
- Correct video_pad tag by @peterchen-intel in #2977
- [JS] Update docs for js package by @Retribution98 in #2968
- Pre-commit test mark removal by @sgonorov in #2921
- Bump pytest from 8.4.2 to 9.0.0 in /tests/python_tests by @dependabot[bot] in #2989
- Bump langchain-core from 1.0.3 to 1.0.4 in /tests/python_tests by @dependabot[bot] in #2990
- Bump actions/dependency-review-action from 4.8.1 to 4.8.2 by @dependabot[bot] in #2995
- Bump optimum-intel from 1.26.0 to 1.26.1 in /tests/python_tests by @dependabot[bot] in #2992
- [tools] ReadME update and fixes by @sbalandi in #2819
- [DOCS] Add TextRerankPipeline to readme.md by @as-suvorov in #2976
- Bump optimum-intel[nncf] from 1.26.0 to 1.26.1 by @dependabot[bot] in #2993
- [wwb] Fix from_onnx for text gen by @sbalandi in #2959
- [Whisper] Rely on timestamps parsing to detect end of chunk by @as-suvorov in #2996
- Bump langchain-community from 0.4 to 0.4.1 in /tests/python_tests by @dependabot[bot] in #2930
- Fix PerfMetrics collection for beam search scenario by @yatarkan in #2943
- Pin OpenVINO runtime commit to avoid circular dependency issues by @CuriousPanCake in #3003
- Fix compile error for Tensor::data() by @praasz in #3009
- Optimize CPU image preprocessing of Phi3 vision by @jade-cho in #2999
- [ImageGeneration] Use device for AutoencoderKL in sample by @as-suvorov in #3020
- Bump js-yaml from 4.1.0 to 4.1.1 in /src/js in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3022
- Text-to-speech use case page by @tsavina in #3017
- Bump langchain-core from 1.0.4 to 1.0.5 in /tests/python_tests by @dependabot[bot] in #3023
- [Docs] Reformat README, remove duplicated sections by @yatarkan in #3018
- Bump js-yaml from 3.14.1 to 3.14.2 in /site in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3027
- Remove usage of deprecated functions by @olpipi in #3011
- Bump actions/checkout from 5.0.0 to 5.0.1 by @dependabot[bot] in #3029
- [GHA] Fix samples dependabot duplicated PRs by @as-suvorov in #3031
- Bump glob from 11.0.1 to 11.1.0 in /.github/actions/install_wheel in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3033
- Add XAttention documentation by @l-bat in #3010
- Update pybind11 to 3.0.1 version by @as-suvorov in #3044
- Complete GenAI Logger by @yangwang201911 in #2879
- Bump Tokenizers by @as-suvorov in #3048
- Fix for deadlock in python callback by @sgonorov in #3034
- Bump langchain-core from 1.0.5 to 1.0.7 in /tests/python_tests in the pip group across 1 directory by @dependabot[bot] in #3054
- Bump pytest from 9.0.0 to 9.0.1 in /tests/python_tests by @dependabot[bot] in #3006
- Base LLM pipeline testing refactoring and optimization by @sgonorov in #2779
- [NPU] Add
batch_sizesupport for embedding model by @mengweiguo in #2986 - Const-related fixes on tesor creation by @sgonorov in #3026
- Fix const in phi3 qwen and minicpm by @sgonorov in #3072
- Bump node-forge from 1.3.1 to 1.3.2 in /site in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3079
- Bump pydantic from 2.12.4 to 2.12.5 by @dependabot[bot] in #3080
- Move SDPAToPA-related functionality to runtime by @CuriousPanCake in #2937
- Kcz/master/support for video in benchmark by @krzyczar in #3019
- [JS] Update tokenizer methods by @Retribution98 in #3012
- Fix for deadlock in python callback by @sgonorov in #3073
- Bump mdast-util-to-hast from 13.2.0 to 13.2.1 in /site in the npm_and_yarn group across 1 directory by @dependabot[bot] in #3091
- Add MileBench validation for VLMs by @l-bat in #2358
- [JS] Bump js package up to 2026.0.0 and update dependecies by @Retribution98 in #3090
- llm_bench: use built in sum by @Wovchena in #3096
- UTF8 validate and replace invalid in GGUF output decoding by @mzegla in #3062
- Use specialized Windows runners by @ababushk in #3098
- [JS] Remove deprecated generate behavior. by @Retribution98 in #3095
- Support json config from file or string by @peterchen-intel in #2912
- Add forceRunPrecommitScope param to Jenkinsfile by @akladiev in #3107
- [wwb] Fix crash on exit() due to loading def dataset for inpainting in streaming mode by @sbalandi in #3103
- Minimal pre-commit implementation by @sgonorov in #3008
- Use ov::Model for phi3.5-vision image preprocessing by @jade-cho in #3063
- [GPU] Use GPU for OV preprocessing of phi4mm by @jade-cho in #3100
- NPU Whisper switch to use stateful pipeline by default by @eshiryae in #3085
- [Docs] Add optimum-cli export command with quantization for Whisper use case page by @yatarkan in #3105
- [wwb] Add possibility to check video inputs for VLM by @sbalandi in #3074
- Fix pre-commit Darker deps and pyi igno...
2025.4.1.0
What's Changed
- Bump product version 2025.4.1 by @akladiev in #3093
- I2I Python deadlock tests and fixes by @sgonorov in #3082
Full Changelog: 2025.4.0.0...2025.4.1.0
2025.4.0.0
What's Changed
- Bump product version 2025.4 by @akladiev in #2620
- Fix CLEANUP_CACHE by @Wovchena in #2617
- [wwb] Add tests for mac/win to ci by @sbalandi in #2603
- xfail embed by @Wovchena in #2618
- Bump py-build-cmake from 0.4.3 to 0.5.0 by @dependabot[bot] in #2624
- Bump actions/upload-pages-artifact from 3.0.1 to 4.0.0 by @dependabot[bot] in #2625
- Bump optimum-intel[nncf] from 1.25.1 to 1.25.2 by @dependabot[bot] in #2613
- Bump optimum-intel from 1.25.1 to 1.25.2 in /tests/python_tests by @dependabot[bot] in #2614
- [GGUF] Fix Q4_1 accuracy by @wine99 in #2563
- [llm bench] Add support of arcee model by @sbalandi in #2636
- Warn about older transformers by @Wovchena in #2634
- Limited max GPU KV-cache considering max allocatable GPU memory size by @popovaan in #2633
- Bump actions/dependency-review-action from 4.7.1 to 4.7.2 by @dependabot[bot] in #2639
- [llm_bench] Override max_length to preserve max_new_tokens by @Wovchena in #2641
- Cache images by @Wovchena in #2629
- Test logging by @Wovchena in #2621
- [CMAKE] Fix samples installation by @mryzhov in #2649
- [JS] Add prettier and align eslint by @almilosz in #2631
- [WWB] Remove use_flash_attention_2 argument for phi4mm by @nikita-savelyevv in #2653
- Implement text embedding pipeline shape fix by @as-suvorov in #2449
- [CMAKE] Solve pybind targets conflict by @mryzhov in #2655
- [GHA] Disable Cacheopt tests on mac by @mryzhov in #2663
- Fix Coverity by @Wovchena in #2601
- Bump peft from 0.17.0 to 0.17.1 in /samples by @dependabot[bot] in #2658
- Bump peft from 0.17.0 to 0.17.1 in /tests/python_tests by @dependabot[bot] in #2660
- downgrade xgrammar version in master by @pavel-esir in #2668
- Extend chat template test models by @yatarkan in #2648
- [NPU]Enable chunk prefill for VLM. by @intelgaoxiong in #2657
- [JS] Add build NodeJS bindings into Manylinux 2_28 by @Retribution98 in #2537
- WWB empty_adapters mode by @likholat in #2671
- Bump actions/dependency-review-action from 4.7.2 to 4.7.3 by @dependabot[bot] in #2674
- Bump aquasecurity/trivy-action from 0.32.0 to 0.33.0 by @dependabot[bot] in #2677
- Bump langchain-core from 0.3.74 to 0.3.75 in /tests/python_tests by @dependabot[bot] in #2673
- Bump actions/download-artifact from 4.3.0 to 5.0.0 by @dependabot[bot] in #2676
- [OV JS] Add perfMetrics grammar getters & update docstrings by @almilosz in #2681
- Bump langchain-community from 0.3.27 to 0.3.29 in /tests/python_tests by @dependabot[bot] in #2680
- Bump actions/checkout from 4.2.2 to 5.0.0 by @dependabot[bot] in #2685
- Fix StructuredOutputConfig pybind11-subgen signatures generation by @pavel-esir in #2669
- [llm_bench] Add start memory info by @sbalandi in #2686
- Updating KVCrush hyperparameters by @gopikrishnajha in #2678
- [Docs] Convert whisper as stateless in the quantization example by @nikita-savelyevv in #2690
- print genai version by @wgzintel in #2684
- Fix initializer for the sparse attention mode by @vshampor in #2689
- Add docs entry about building GenAI with free threaded Python by @p-wysocki in #2679
- Reduce structured output controller mutex locking scope by @mzegla in #2687
- [speculative decoding] Move from ManualTimer to pure metrics by @sbalandi in #2695
- [CI] [GHA] Use custom
actions/download-artifactaction with the fixed retries logic by @akashchi in #2692 - Enable VLM generation on NPU without image input by @AlexanderKalistratov in #2694
- [llm bench] Add possibility to setup cache eviction config for LLM by @sbalandi in #2693
- Remove not supported rerank models from docs by @as-suvorov in #2702
- Tune automatic memory allocation by @popovaan in #2697
- Bump actions/setup-python from 5.6.0 to 6.0.0 by @dependabot[bot] in #2705
- Bump pytest from 8.4.1 to 8.4.2 in /tests/python_tests by @dependabot[bot] in #2710
- [WWB] friendly error message for wrong model type by @isanghao in #2672
- [CI] [GHA] Use smaller runners for image generation samples by @akashchi in #2682
- Add image generation pipeline reuse into README by @JohnLeFeng in #2701
- Align benchmark_vlm.py and cpp by @Wovchena in #2711
- [CI] Fix NodeJS tests for manylinux by @Retribution98 in #2715
- fix checking tokenizers version by @pavel-esir in #2667
- Optimize qwen2vl encoder by @WeldonWangwang in #2630
- Check available memory before allocating KV-cache. by @popovaan in #2683
- Fixed clearing of kv-cache for GPU by @popovaan in #2717
- [GHA] w/a to build ov samples by @mryzhov in #2734
- [OV JS] Initial support for SchedulerConfig by @almilosz in #2696
- Test LLM samples with GGUF models by @Retribution98 in #2464
- [llm_bench] LLMPipeline fix negative time by @sbalandi in #2742
- Bump pydantic from 2.11.7 to 2.11.9 in /samples by @dependabot[bot] in #2732
- [llm bench] Add mem info on initial/compilation phase to json/csv by @sbalandi in #2741
- Increase timeouts by @Wovchena in #2743
- Allow additional_params for tokenizer decode in TextStreamer by @dkalinowski in #2729
- Fix attention mask pass for whisper (static) by @eshiryae in #2665
- Support from-onnx parameter by @sstrehlk in #2441
- Use model path property for caching by @praasz in #2720
- Increase GGUF timeouts by @Wovchena in #2756
- [VLM] Fixed measuring of embeddings preparation. by @popovaan in #2752
- Bump timm from 1.0.19 to 1.0.20 by @dependabot[bot] in #2754
- [llm_bench] Fix OpenVINO config not being passed for speech-to-text and Whisper models by @aobolensk in #2763
- OPT & Clean code of openvino_vision_embeddings_merger_model inputs processing by @zhaixuejun1993 in #2726
- Add .github/pull_request_template.md by @Wovchena in #2765
- Update transformers to 4.53.3 by @as-suvorov in https://gi...
2025.3.0.0
What's Changed
- Bump product version 2025.3 by @akladiev in #2255
- Implement SnapKV by @vshampor in #2067
- [WWB] Additional processing of native phi4mm by @nikita-savelyevv in #2276
- Update ov genai version in samples by @as-suvorov in #2275
- use chat templates in vlm by @eaidova in #2279
- Fix 'Unsupported property' fails if set prompt_lookup to False by @sbalandi in #2240
- Force the PA implementation in the llm-bench by default by @sbalandi in #2271
- Update Whisper README.md as "--disable-stateful" is no longer required to export models for NPU by @luke-lin-vmc in #2249
- Removed 'slices' from EncodedImage by @popovaan in #2258
- support text embeddings in llm_bench by @eaidova in #2269
- [wwb]: load transformers model first, then only trust_remote_code by @eaidova in #2270
- [GHA] Coverity pipeline fixes by @mryzhov in #2283
- [GHA][DEV] Fixed coverity path creation by @mryzhov in #2285
- [GHA][DEV]Save coveity tool to cache by @mryzhov in #2286
- [GHA][DEV] Set cache key for coverity tool by @mryzhov in #2288
- Image generation multiconcurrency (#2190) by @dkalinowski in #2284
- [GGUF] Support GGUF format for tokenizers and detokenizers by @rkazants in #2263
- Unskip whisper tests & update optimum-intel by @as-suvorov in #2247
- Update README.md with text-to-speech by @rkazants in #2294
- add new chat template for qwen3 by @eaidova in #2297
- [DOCS] Correct cmd-line for TTS conversion by @rkazants in #2303
- [GHA] Enabled product manifest.yml by @mryzhov in #2281
- Bump the npm_and_yarn group across 3 directories with 2 updates by @dependabot[bot] in #2309
- [GHA] Save artifacts to cloud share by @akladiev in #1943
- [GHA][[COVERITY] added manual trigger by @mryzhov in https://github.com//pull/2289
- [GHA] Fix missing condition for Extract Artifacts step by @akladiev in #2313
- [llm bench] Turn off PA backend for VLM by @sbalandi in #2312
- [llm_bench] Add setting of max_num_batched_tokens for SchedulerConfig by @sbalandi in #2316
- [GHA] Fix missing condition for LLM & VLM test by @sammysun0711 in #2326
- [Test] Skip gguf test on MacOS due to sporadic failure by @sammysun0711 in #2328
- [GGUF] support Qwen3 architecture by @TianmengChen in #2273
- [llm_bench] Increase max_num_batched_tokens to the largest positive integer by @sbalandi in #2327
- Bump aquasecurity/trivy-action from 0.30.0 to 0.31.0 by @dependabot[bot] in #2310
- Bump actions/download-artifact from 4.1.9 to 4.3.0 by @dependabot[bot] in #2315
- Fix system_message forwarding by @Wovchena in #2325
- Disabled crop of the prompt for minicpmv. by @andreyanufr in #2320
- [llm bench] Fix setting ATTENTION_BACKEND to plugin config in case of fallback to Optimum by @sbalandi in #2332
- Bump brace-expansion from 2.0.1 to 2.0.2 in /.github/actions/install_wheel in the npm_and_yarn group across 1 directory by @dependabot[bot] in #2338
- Fix multinomial sampling for PromptLookupDecoding by @sbalandi in #2331
- [llm bench] Avoid using not supported by beam_search parameters for beam_search case by @sbalandi in #2336
- Update Export Requirements by @apaniukov in #2342
- [GGUF] Serialize Generated OV Model for Faster LLMPipeline Init by @sammysun0711 in #2218
- Fixed system message in chat mode. by @popovaan in #2343
- Bump librosa from 0.10.2.post1 to 0.11.0 in /samples by @dependabot[bot] in #2346
- [Test][GGUF] Add DeepSeek-R1-Distill-Qwen GGUF in CI by @sammysun0711 in #2329
- [llm_bench] Remove default scheduler config by @sbalandi in #2341
- master: add Phi-4-multimodal-instruct by @Wovchena in #2264
- Fix paths with unicode for tokenizers by @yatarkan in #2337
- [WWB] Add try-except block for processor loading by @nikita-savelyevv in #2352
- [WWB] Bring back eager attention implementation by default by @nikita-savelyevv in #2353
- fix supported models link in TTS samples by @eaidova in #2300
- StaticLLMPipeline: Add tests on caching by @smirnov-alexey in #1905
- [WWB] Fix loading the tokenizer for VLMs by @l-bat in #2351
- Pass Scheduler Config for VLM Pipeline in WhoWhatBenchmark. by @popovaan in #2318
- Remove misspelled CMAKE_CURRENT_SOUCE_DIR by @Wovchena in #2362
- Increase timeout for LLM & VLM by @Wovchena in #2359
- [llm bench] Fix setting ATTENTION_BACKEND to plugin config in case of fallback to Optimum for VLM by @sbalandi in #2361
- Support multi images for vlm benchmarking in samples and llm_bench by @wgzintel in #2197
- CB: Hetero pipeline parallel support by @WeldonWangwang in #2227
- Update conversion instructions by @adrianboguszewski in #2287
- Merge stderr from failed samples by @Wovchena in #2156
- Revert cache folder by @Wovchena in #2372
- Update README in Node.js API by @almilosz in #2374
- [Docs] Rework home page by @yatarkan in #2368
- Align PromptLookupDecoding with greedy when dynamic_split_fuse works by @sbalandi in #2360
- Support to collect latency for transformers V4.52.0 by @wgzintel in #2373
- Bump diffusers from 0.33.1 to 0.34.0 in /samples by @dependabot[bot] in #2381
- Bump diffusers from 0.33.1 to 0.34.0 in /tests/python_tests by @dependabot[bot] in #2380
- Structured Output generation with
XGrammarby @pavel-esir in #2295 - Disable XGrammar on Android by @apaniukov in #2389
- [wwb] Take prompts from different categories for def dataset for VLM by @sbalandi in #2349
- Fix for cloning NPU Image Generation pipelines (#2376) by @dkalinowski in #2393
- Set add_special_tokens=false for image tags in MiniCPM. by @popovaan in #2404
- Fix missing use cases for inpainting models and defining use case with relative path by @sbalandi in #2387
- temporary skip failing whisper tests by @pavel-esir in #2396
- Fix test_vlm_npu_no_exception by @AlexanderKalistratov in #2388
- Bump timm from 1.0.15 to 1.0.16 by @dependabot[bot] in #2390
- Optimize VisionEncoderQwen2VL::encode by @usst...