You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: libraries/dl-streamer/RELEASE_NOTES.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -30,8 +30,8 @@ The complete solution leverages:
30
30
|[gvatrack](./docs/source/elements/gvatrack.md)| Performs object tracking using zero-term, or imageless tracking algorithms. Assigns unique object IDs to the tracked objects. |
31
31
|[gvawatermark](./docs/source/elements/gvawatermark.md)| Overlays the metadata on the video frame to visualize the inference results. |
32
32
33
-
For the details on supported platforms, please refer to [System Requirements](./get_started/system_requirements.md).
34
-
For installing Pipeline Framework with the prebuilt binaries or Docker\* or to build the binaries from the open source, refer to [Intel® DL Streamer Pipeline Framework installation guide](./get_started/install/install_guide_index.md).
33
+
For the details on supported platforms, please refer to [System Requirements](./docs/source/get_started/system_requirements.md).
34
+
For installing Pipeline Framework with the prebuilt binaries or Docker\* or to build the binaries from the open source, refer to [Intel® DL Streamer Pipeline Framework installation guide](./docs/source/get_started/install/install_guide_index.md).
35
35
36
36
### New in this Release
37
37
| Title | High-level description |
@@ -41,11 +41,11 @@ For installing Pipeline Framework with the prebuilt binaries or Docker\* or to b
41
41
| Gvagenai element added | Performs inference with Vision Language Models using OpenVINO™ GenAI, accepts video and text prompt as an input, and outputs text description. <br>Models supported: MiniCPM-V, Gemma3, Phi-4-multimodal-instruct. |
42
42
| Deep SORT | Preview version of Deep SORT tracking algorithm in gvatrack element. |
43
43
| gvawatermark element support on GPU | Gvawatermark implementation extended about GPU support (CPU default). |
44
-
| Pipeline optimizer support | 1st version of DLStreamer optimizer implementation added allowing end user finding the most FPS optimized pipeline. |
44
+
| Pipeline optimizer support | 1st version of DL Streamer optimizer implementation added allowing end user finding the most FPS optimized pipeline. |
45
45
| GstAnalytics metadata support | Enabled GstAnalytics metadata support. |
46
46
| OpenVINO custom operations | Add support for OpenVINO custom operations. |
47
47
| D3D11 preprocessing enabled | Windows support extended about D3D11 preprocessing implementation. |
48
-
| UX, Stability && Performance fixes | • memory leaks fixes <br> • automatically select pre-process-backend=va-surface-sharing for GPU <br>• adjust caps negotiations and preproc backend selection <br>• removing deleted element from all shared reference lists. <br> • useOpenCV preproc to convert sparse tensors to contiguous tensors <br>• creation of new VADisplay ctx per each inference instance <br>• remove need for dual va+opencv image pre-processing |
48
+
| UX, Stability && Performance fixes | • memory management fixes <br> • automatically select pre-process-backend=va-surface-sharing for GPU <br>• adjusting caps negotiations and preproc backend selection <br>• removing deleted element from all shared reference lists. <br> • using OpenCV preproc to convert sparse tensors to contiguous tensors <br>• creation of new VADisplay ctx per each inference instance <br>• remove need for dual va+opencv image pre-processing |
49
49
| Intel Core Ultra Panther Lake CPU/GPU support | Readiness for supporting Intel Core Ultra Panther Lake CPU/GPU. |
0 commit comments