Release Notes update for 2026.0 by tbujewsk · Pull Request #708 · open-edge-platform/dlstreamer

tbujewsk · 2026-03-18T16:25:38Z

Description

Please include a summary of the changes and the related issue. List any dependencies that are required for this change.

Fixes # (issue)

Any Newly Introduced Dependencies

Please describe any newly introduced 3rd party dependencies in this change. List their name, license information and how they are used in the project.

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

Checklist:

I agree to use the MIT license for my code changes.
I have not introduced any 3rd party components incompatible with MIT.
I have not included any company confidential information, trade secret, password or security token.
I have performed a self-review of my code.

…ancements, and deprecations

…elease notes

nszczygl9 · 2026-03-18T19:42:25Z

docs/source/release-notes.md

@@ -57,35 +57,42 @@ For installing Pipeline Framework with the prebuilt binaries or Docker\* or to b
 | YOLOv26 model support|	Added converters and post-processing for YOLOv26 models, including oriented bounding box (OBB) support and FP16/FP32 GPU inference. Added YOLOv26 to supported models in samples.|


I think it's not true. Yolo26 OBB FP16/FP32 is not supported on GPU. It's OpenVINO problem. Only INT8 work correctly

tjanczak · 2026-03-19T08:39:23Z

docs/source/release-notes.md

Please either remove "including OBB", or add information that all variants are supported (detect, classify, pose, segmenation and obb)

Please add also information on 'streamlined integration" with Ultralytics model hub and HuggingFace model hub

Please also add yolo-e to the list of new supported models.

tjanczak · 2026-03-19T08:40:07Z

docs/source/release-notes.md

@@ -57,35 +57,42 @@ For installing Pipeline Framework with the prebuilt binaries or Docker\* or to b
 | YOLOv26 model support|	Added converters and post-processing for YOLOv26 models, including oriented bounding box (OBB) support and FP16/FP32 GPU inference. Added YOLOv26 to supported models in samples.|


Please either remove "including OBB", or add information that all variants are supported (detect, classify, pose, segmenation and obb). Please remove "FP16/FP32 support" - all formats are supported, including INT8.

tjanczak · 2026-03-19T08:41:55Z

docs/source/release-notes.md

What is "FP32 precision" enhanement? What is "custom GSTAnalytics data API"?
I'd suggest to write DLStreamer supports GstAanalytics metadata for object detection, classification and tracking + adds custom GstAnalytics extension for keypoints

tjanczak · 2026-03-19T08:50:09Z

docs/source/release-notes.md

+| FP32 precision in BoxesLabelsConverter	| Added FP32 precision support in BoxesLabelsConverter label parsing.|
+| Bounding box validation |	Added extra validation of bounding boxes to improve robustness.|
+| OpenCV tensor compression for all devices	| Use OpenCV tensor compression for all inference devices, yielding best performance across CPU/GPU/NPU.|
+| Model API refactoring	| Moved Model API parser to separate files; added conversion from third-party metadata to Model API.|


"third-party metadata" -> "Ultralytics and HuggingFace metadata"

tjanczak · 2026-03-19T08:51:05Z

docs/source/release-notes.md

@@ -57,35 +57,42 @@ For installing Pipeline Framework with the prebuilt binaries or Docker\* or to b
 | YOLOv26 model support|	Added converters and post-processing for YOLOv26 models, including oriented bounding box (OBB) support and FP16/FP32 GPU inference. Added YOLOv26 to supported models in samples.|
 | RT-DETR model support |	Added RT-DETR support with dedicated converter implementation for real-time detection transformer models. |


Remove "dedicated converter", support is more than just converter, it includes also parsing of HuggingFace pre-processor config file + conversion from HuggingFace to OpenVINO.

tjanczak · 2026-03-19T08:51:59Z

docs/source/release-notes.md

-| OpenCV tensor compression for all devices	| Use OpenCV tensor compression for all inference devices, yielding best performance across CPU/GPU/NPU.|
-| Model API refactoring	| Moved Model API parser to separate files; added conversion from third-party metadata to Model API.|
 | VLM Alerts sample (Python) | New Python sample for VLM-based alerts with displaying results on produced video. |
 | Smart NVR sample (Python)	 | New Python sample for Smart NVR with prototype elements. |


replace "prototype elements" with actual information on what this sample does.

tjanczak · 2026-03-19T08:54:07Z

docs/source/release-notes.md

+| gvawatermark enhancements|	Major enhancements to the gvawatermark element: display configuration options (thickness, color index), text background support, inclusive/exclusive label filtering, additional font support, average FPS info overlay, and visual documentation.|
+| DLS Optimizer enhancements	 | Optimizer refactored with multi-stream optimization, cross-stream batching, improved FPS reporting, and device selection improvements. |
+| gvametaconvert enhancements| Added reference timestamp meta extraction to gvametaconvert element.|
+| Custom GstAnalytics data | Enabled custom code to add GstAnalytics data outside of DL Streamer components.|


I don't understand what are we tryign to say here; please document supported GstAnalytics APIs and Intel extensions.

tjanczak · 2026-03-19T08:55:25Z

docs/source/release-notes.md

 | Preview Architecture 2.0 Samples | Preview Arch 2.0 samples have known issues with inference results. |

+
+## Deprecation And Support


Rename to "Legacy Features and Deprecation Timeline"

tjanczak · 2026-03-19T08:56:33Z

docs/source/release-notes.md

+|---|---|---|
+| OMZ models |	end of Q3'2026	| Use HuggingFace, Ultralytics, TIMM |
+| Model-proc-file| 	end of Q3'2026	| ModelAPI (common with Geti) |
+| GstVideoRegionOfInterest meta + Intel extensions |	end of Q4'2026 |	GstAnalyticsMtd (aka new Collabora meta) |


Do not use statements like "aka new Collabora meta" in official release notes

tjanczak · 2026-03-19T08:56:55Z

docs/source/release-notes.md

+| OMZ models |	end of Q3'2026	| Use HuggingFace, Ultralytics, TIMM |
+| Model-proc-file| 	end of Q3'2026	| ModelAPI (common with Geti) |
+| GstVideoRegionOfInterest meta + Intel extensions |	end of Q4'2026 |	GstAnalyticsMtd (aka new Collabora meta) |
+| Architecture 2.0 elements |	end of Q4'2026 |	need to take valuable elements/ideas and deprecate others |


do not use "need to take valuable elements" in official release notes; reword to more formal statement

oonyshch · 2026-03-19T10:58:20Z

docs/source/release-notes.md

+| Bounding box validation |	Added extra validation of bounding boxes to improve robustness.|
+| OpenCV tensor compression for all devices	| Use OpenCV tensor compression for all inference devices, yielding best performance across CPU/GPU/NPU.|
+| Model API refactoring	| Moved Model API parser to separate files; added conversion from third-party metadata to Model API.|
 | Python samples overview	 | Added overview section for Python samples; updated READMEs. |


Also we have introduced several new python samples to the codebase. Maybe we should mention them here?

there are listed in the 'New in this Release' section

Fact, thanks, saw that.

Also there was this Windows sample
If it's a part of the release, we should add information about it.

There were pipeline graphs added for all Windows samples too (not sure about mentioning, because all new python samples were merged with such graphs and we don't seem to highlight that)

Added info about Windows sample.

docs/source/release-notes.md

Co-authored-by: Olena Onyshchenko <olena.onyshchenko@intel.com>

docs/source/release-notes.md

Co-authored-by: Olena Onyshchenko <olena.onyshchenko@intel.com>

oonyshch

LGTM, all links across file work, I double-checked 👍

tbujewsk added 2 commits March 18, 2026 17:24

[DOCS] Update release notes for version 2026.0 with new features, enh…

2c3730c

…ancements, and deprecations

[DOCS] Remove deprecated architecture 2.0 elements from release notes

aee21ab

tbujewsk marked this pull request as ready for review March 18, 2026 16:25

tbujewsk requested review from a team, BaoHuiling, OskarFiedot, ZiningLi, dmichalo, jmotow, marcin-wadolkowski, mholowni, msmiatac, nszczygl9, oonyshch, pbartosik, qianlongding, walidbarakat, yangjianfeng1208 and yunowo as code owners March 18, 2026 16:25

[DOCS] Update deprecation timeline for Architecture 2.0 elements in r…

f6b46a4

…elease notes

jmotow approved these changes Mar 18, 2026

View reviewed changes

nszczygl9 reviewed Mar 18, 2026

View reviewed changes

fix per review

4a1ce01

tjanczak requested changes Mar 19, 2026

View reviewed changes

oonyshch reviewed Mar 19, 2026

View reviewed changes

docs/source/release-notes.md Outdated Show resolved Hide resolved

oonyshch requested changes Mar 19, 2026

View reviewed changes

tbujewsk and others added 2 commits March 19, 2026 12:14

Apply suggestion from @oonyshch

24a8ad6

Co-authored-by: Olena Onyshchenko <olena.onyshchenko@intel.com>

review fixes #2

8f453e1

oonyshch reviewed Mar 19, 2026

View reviewed changes

docs/source/release-notes.md Outdated Show resolved Hide resolved

oonyshch reviewed Mar 19, 2026

View reviewed changes

docs/source/release-notes.md Outdated Show resolved Hide resolved

oonyshch reviewed Mar 19, 2026

View reviewed changes

docs/source/release-notes.md Outdated Show resolved Hide resolved

tbujewsk and others added 5 commits March 19, 2026 12:55

review fixes #3

dd8e9ce

Apply suggestion from @oonyshch

21227d8

Co-authored-by: Olena Onyshchenko <olena.onyshchenko@intel.com>

Apply suggestion from @oonyshch

1d3e7f1

Co-authored-by: Olena Onyshchenko <olena.onyshchenko@intel.com>

Apply suggestion from @oonyshch

8799448

Co-authored-by: Olena Onyshchenko <olena.onyshchenko@intel.com>

review fixes #4

433e386

tbujewsk requested review from oonyshch and tjanczak March 19, 2026 12:09

oonyshch approved these changes Mar 19, 2026

View reviewed changes

		@@ -57,35 +57,42 @@ For installing Pipeline Framework with the prebuilt binaries or Docker\* or to b
		\| YOLOv26 model support\| Added converters and post-processing for YOLOv26 models, including oriented bounding box (OBB) support and FP16/FP32 GPU inference. Added YOLOv26 to supported models in samples.\|

		@@ -57,35 +57,42 @@ For installing Pipeline Framework with the prebuilt binaries or Docker\* or to b
		\| YOLOv26 model support\| Added converters and post-processing for YOLOv26 models, including oriented bounding box (OBB) support and FP16/FP32 GPU inference. Added YOLOv26 to supported models in samples.\|
		\| RT-DETR model support \| Added RT-DETR support with dedicated converter implementation for real-time detection transformer models. \|

		\| Preview Architecture 2.0 Samples \| Preview Arch 2.0 samples have known issues with inference results. \|


		## Deprecation And Support

Conversation

tbujewsk commented Mar 18, 2026

Description

Any Newly Introduced Dependencies

How Has This Been Tested?

Checklist:

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

oonyshch left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants

oonyshch left a comment •

edited

Loading