Skip to content

chore(deps): bump the openvino-inference-stack group with 3 updates - #53

Open
dependabot[bot] wants to merge 1 commit into
devfrom
dependabot/pip/dev/openvino-inference-stack-f5108819a5
Open

chore(deps): bump the openvino-inference-stack group with 3 updates#53
dependabot[bot] wants to merge 1 commit into
devfrom
dependabot/pip/dev/openvino-inference-stack-f5108819a5

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Oct 5, 2026

Copy link
Copy Markdown
Contributor

Bumps the openvino-inference-stack group with 3 updates: openvino-genai, openvino and openvino-tokenizers.

Updates openvino-genai from 2026.2.1.0 to 2026.4.1.0

Release notes

Sourced from openvino-genai's releases.

2026.4.1

Summary of major features and improvements

  • Improved GroupQueryAttention support for large language models served through the ONNX frontend:
    • Added causal-attention and partial rotary-embedding support to GroupQueryAttention, broadening coverage of modern LLMs.
    • Extended MatMulNBits with bfloat16 support and reordered weight/scale/zero-point layouts for correct decoding of more quantized models.
    • Fixed correctness issues in the sliding-window KV-cache path that could produce wrong results:
      • an out-of-bounds ScatterUpdate index that could cause memory corruption or a driver crash on GPUs,
      • incorrect Gather shape inference for f8e4m3 and other low-precision data types (f8e4m3 Gather is now enabled for the windowed KV-cache).
  • Fixed issues:
    • GPU:
      • Fixed wrong or corrupted results when using remote (zero-copy) output tensors with a transpose at the model output under dynamic shapes.
      • Fixed GRU sequence (RNN) models producing incorrect results with dynamic shapes, and corrected blocked-format reorder offsets.
      • Fixed recursive layout/format propagation through Reshape nodes during GPU graph compilation.
    • NPU:
      • ID 233822: Fixed unexpected application crashes on Intel® Core™ Ultra Series 3 processors on Windows that could occur with certain Intel® NPU PV drivers (32.0.100.4300, 32.0.100.4509, and 32.0.100.4512). It is recommended to migrate to OV 2026.4.1 in case the issue is observed with OV releases 2026.2, 2026.3, or 2026.4.
      • Hardened compiled-blob import against malformed or forged blobs: fixed a possible integer overflow in metadata parsing, bounded recursion in the compatibility-string parser, and rejected forged blobs on import.
    • CPU:
      • The OV_CPU_MAX_ISA instruction-set cap now works in release builds (previously debug-only) and is modeled as a feature bitmask.
      • Aligned JIT kernel selection with the OV_CPU_MAX_ISA cap so operators produce correct results when the ISA is capped.
    • Core / Frontends:
      • Hardened operators against malformed inputs: added index validation to ScatterElementsUpdate, divide-by-zero and overflow guards to Col2Im shape inference, and axes validation preventing a potential out-of-bounds write in the ONNX Pad operator.

You can find the OpenVINO™ toolkit 2026.4.1 release here:

Release documentation is available here: https://docs.openvino.ai/2026

Release Notes are available here: https://docs.openvino.ai/2026/about-openvino/release-notes-openvino.html

*Other names and brands may be claimed as the property of others.

2026.4.0

Summary of major features and improvements  

  • More GenAI coverage and framework integrations to minimize code changes

    • New models supported:
      • On CPU: Gemma-3n
      • On CPU, GPU: Kokoro-82M, Qwen3-VL-4B with EAGLE-3, Qwen3-ASR, Muse Glimmer 30B, Qwen3.8 27B, Gemma 4 12B, Hy-MT2-1.8B, DeepSeek OCR-2, and Granite 4.0 H Micro
      • On NPUs: FLUX.2-Klein 4B and Kokoro-82M
    • Additional CPU and GPU-enabled models available as early releases: Qwen-Image, Z-Image-Turbo, Granite 4.0 H Tiny, Fun-ASR-Nano, LFM2.5-8B-A1B, MiniCPM5-2B, RF-DETR, BGE Reranker-V2-M3, and BGE M3

  • Broader LLM model support and more model compression techniques

    • OpenVINO™ GenAI adds Multi-Token Prediction (MTP) speculative decoding for Gemma 4, Qwen3.5, and Qwen3.6 on CPUs and GPUs, enabling higher throughput and lower latency without sacrificing accuracy.
    • Preview: OpenVINO™ GenAI introduces DFlash acceleration for Qwen models on GPUs, and visual-token support to reduce latency and speed up GenAI pipelines on Intel® Core™ Ultra Series 3 processors.
    • With Tree Drafting (Top-K) for EAGLE-3 now supported in OpenVINO™ GenAI, developers can unlock higher throughput on VLM pipelines compared to Chain Drafting (Top-1).
    • Xe3 integrated graphics optimizations in OpenVINO™ GenAI improve AI inference performance for Gemma 4 models processing long-context inputs on Intel® Core™ Ultra Series 3 processors.

... (truncated)

Commits
  • e213a14 [CPU] Enable OV_CPU_MAX_ISA in release builds and model the cap as an ISA fea...
  • d79bee5 [NPU] CiP 2026/4 WW39 (#38337)
  • daf8385 Docs- Update NPU Known Issue (#38341)
  • eff71bc New FAQ section, Accuracy table and system descriptions added for OV-… (#38200)
  • 6e50064 [NPU][IE-MDK] Update Skip Config for BlobCompatibilty tests (#38329)
  • 20dc4bd [CPU] Align JIT kernel selection with ov::with_cpu_x86_*() (2026.4 branch) ...
  • c577b3c Remove LLM Accuracy from required
  • ee773f3 RPM: Bump cmake samples dependency (#38327)
  • 6dc59a1 Bump product version 2026.4.1 (#38302)
  • 4bc97a8 [GPU] Prevent dynamic remote outputs from aliasing permute producers (backpor...
  • Additional commits viewable in compare view

Updates openvino from 2026.2.1 to 2026.4.1

Release notes

Sourced from openvino's releases.

2026.4.1

Summary of major features and improvements

  • Improved GroupQueryAttention support for large language models served through the ONNX frontend:
    • Added causal-attention and partial rotary-embedding support to GroupQueryAttention, broadening coverage of modern LLMs.
    • Extended MatMulNBits with bfloat16 support and reordered weight/scale/zero-point layouts for correct decoding of more quantized models.
    • Fixed correctness issues in the sliding-window KV-cache path that could produce wrong results:
      • an out-of-bounds ScatterUpdate index that could cause memory corruption or a driver crash on GPUs,
      • incorrect Gather shape inference for f8e4m3 and other low-precision data types (f8e4m3 Gather is now enabled for the windowed KV-cache).
  • Fixed issues:
    • GPU:
      • Fixed wrong or corrupted results when using remote (zero-copy) output tensors with a transpose at the model output under dynamic shapes.
      • Fixed GRU sequence (RNN) models producing incorrect results with dynamic shapes, and corrected blocked-format reorder offsets.
      • Fixed recursive layout/format propagation through Reshape nodes during GPU graph compilation.
    • NPU:
      • ID 233822: Fixed unexpected application crashes on Intel® Core™ Ultra Series 3 processors on Windows that could occur with certain Intel® NPU PV drivers (32.0.100.4300, 32.0.100.4509, and 32.0.100.4512). It is recommended to migrate to OV 2026.4.1 in case the issue is observed with OV releases 2026.2, 2026.3, or 2026.4.
      • Hardened compiled-blob import against malformed or forged blobs: fixed a possible integer overflow in metadata parsing, bounded recursion in the compatibility-string parser, and rejected forged blobs on import.
    • CPU:
      • The OV_CPU_MAX_ISA instruction-set cap now works in release builds (previously debug-only) and is modeled as a feature bitmask.
      • Aligned JIT kernel selection with the OV_CPU_MAX_ISA cap so operators produce correct results when the ISA is capped.
    • Core / Frontends:
      • Hardened operators against malformed inputs: added index validation to ScatterElementsUpdate, divide-by-zero and overflow guards to Col2Im shape inference, and axes validation preventing a potential out-of-bounds write in the ONNX Pad operator.

You can find the OpenVINO™ toolkit 2026.4.1 release here:

Release documentation is available here: https://docs.openvino.ai/2026

Release Notes are available here: https://docs.openvino.ai/2026/about-openvino/release-notes-openvino.html

*Other names and brands may be claimed as the property of others.

2026.4.0

Summary of major features and improvements  

  • More GenAI coverage and framework integrations to minimize code changes

    • New models supported:
      • On CPU: Gemma-3n
      • On CPU, GPU: Kokoro-82M, Qwen3-VL-4B with EAGLE-3, Qwen3-ASR, Muse Glimmer 30B, Qwen3.8 27B, Gemma 4 12B, Hy-MT2-1.8B, DeepSeek OCR-2, and Granite 4.0 H Micro
      • On NPUs: FLUX.2-Klein 4B and Kokoro-82M
    • Additional CPU and GPU-enabled models available as early releases: Qwen-Image, Z-Image-Turbo, Granite 4.0 H Tiny, Fun-ASR-Nano, LFM2.5-8B-A1B, MiniCPM5-2B, RF-DETR, BGE Reranker-V2-M3, and BGE M3

  • Broader LLM model support and more model compression techniques

    • OpenVINO™ GenAI adds Multi-Token Prediction (MTP) speculative decoding for Gemma 4, Qwen3.5, and Qwen3.6 on CPUs and GPUs, enabling higher throughput and lower latency without sacrificing accuracy.
    • Preview: OpenVINO™ GenAI introduces DFlash acceleration for Qwen models on GPUs, and visual-token support to reduce latency and speed up GenAI pipelines on Intel® Core™ Ultra Series 3 processors.
    • With Tree Drafting (Top-K) for EAGLE-3 now supported in OpenVINO™ GenAI, developers can unlock higher throughput on VLM pipelines compared to Chain Drafting (Top-1).
    • Xe3 integrated graphics optimizations in OpenVINO™ GenAI improve AI inference performance for Gemma 4 models processing long-context inputs on Intel® Core™ Ultra Series 3 processors.

... (truncated)

Commits
  • e213a14 [CPU] Enable OV_CPU_MAX_ISA in release builds and model the cap as an ISA fea...
  • d79bee5 [NPU] CiP 2026/4 WW39 (#38337)
  • daf8385 Docs- Update NPU Known Issue (#38341)
  • eff71bc New FAQ section, Accuracy table and system descriptions added for OV-… (#38200)
  • 6e50064 [NPU][IE-MDK] Update Skip Config for BlobCompatibilty tests (#38329)
  • 20dc4bd [CPU] Align JIT kernel selection with ov::with_cpu_x86_*() (2026.4 branch) ...
  • c577b3c Remove LLM Accuracy from required
  • ee773f3 RPM: Bump cmake samples dependency (#38327)
  • 6dc59a1 Bump product version 2026.4.1 (#38302)
  • 4bc97a8 [GPU] Prevent dynamic remote outputs from aliasing permute producers (backpor...
  • Additional commits viewable in compare view

Updates openvino-tokenizers from 2026.2.1.0 to 2026.4.1.0

Release notes

Sourced from openvino-tokenizers's releases.

2026.4.1.0

What's Changed

Full Changelog: openvinotoolkit/openvino_tokenizers@2026.4.0.0...2026.4.1.0

2026.4.0.0

What's Changed

New Contributors

Full Changelog: openvinotoolkit/openvino_tokenizers@2026.3.1.0...2026.4.0.0

2026.3.0.0

What's Changed

New Contributors

Full Changelog: openvinotoolkit/openvino_tokenizers@2026.2.1.0...2026.3.0.0

Commits
  • 9bfda52 Bump product version 2026.4.1 (#768)
  • afe0885 Update PCRE2 (#765)
  • a04accf Bump tiktoken from 0.13.0 to 0.14.0 (#734)
  • 8dbd967 Fix ByteDance-Seed/academic-ds-9B and Update CLI Tools (#729)
  • caefc0d Bump ruff from 0.16.3 to 0.16.4 (#732)
  • 7121343 [JS] Bump NPM version up to 2026.4.0 (#728)
  • 38ef789 [Tokenizers] Register RegexNormalization and Sentencepiece ops in the op fact...
  • c829786 Bump ruff from 0.16.1 to 0.16.3 (#726)
  • 443157c Bump astral-sh/setup-uv from 9.0.0 to 10.0.1 (#725)
  • c478b92 Fix a crash in CharsMapNormalization on macOS (#727)
  • Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

  • @dependabot rebase will rebase this PR
  • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
  • @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
  • @dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
  • @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
  • @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
  • @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
  • @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions

@dependabot
chore(deps): bump the openvino-inference-stack group with 3 updates
c929d11 
Bumps the openvino-inference-stack group with 3 updates: [openvino-genai](https://github.com/openvinotoolkit/openvino), [openvino](https://github.com/openvinotoolkit/openvino) and [openvino-tokenizers](https://github.com/openvinotoolkit/openvino_tokenizers).


Updates `openvino-genai` from 2026.2.1.0 to 2026.4.1.0
- [Release notes](https://github.com/openvinotoolkit/openvino/releases)
- [Changelog](https://github.com/openvinotoolkit/openvino/blob/master/docs/RELEASE.MD)
- [Commits](openvinotoolkit/openvino@2026.2.1...2026.4.1)

Updates `openvino` from 2026.2.1 to 2026.4.1
- [Release notes](https://github.com/openvinotoolkit/openvino/releases)
- [Changelog](https://github.com/openvinotoolkit/openvino/blob/master/docs/RELEASE.MD)
- [Commits](openvinotoolkit/openvino@2026.2.1...2026.4.1)

Updates `openvino-tokenizers` from 2026.2.1.0 to 2026.4.1.0
- [Release notes](https://github.com/openvinotoolkit/openvino_tokenizers/releases)
- [Commits](openvinotoolkit/openvino_tokenizers@2026.2.1.0...2026.4.1.0)

---
updated-dependencies:
- dependency-name: openvino-genai
  dependency-version: 2026.4.1.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: openvino-inference-stack
- dependency-name: openvino
  dependency-version: 2026.4.1
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: openvino-inference-stack
- dependency-name: openvino-tokenizers
  dependency-version: 2026.4.1.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
  dependency-group: openvino-inference-stack
...

Signed-off-by: dependabot[bot] <support@github.com>
@dependabot @github

dependabot Bot commented on behalf of github Oct 5, 2026

Copy link
Copy Markdown
Contributor Author

Labels

The following labels could not be found: dependencies. Please create it before Dependabot can add it to a pull request.

Please fix the above issues or remove invalid values from dependabot.yml.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

0 participants