openvino

openvino copied to clipboard

scalar_tensor.default op name support (non aten version)

2

### Details: - "aten.scalar_tensor.default" is already supported by pytorch frontend. But some ops seems to have "scalar_tensor.default" ops in executorch flow which uses same translation as "aten.scalar_tensor.default". The PR only...

cavusmustafa

[GPU] XeTLA based LoRA kernel

8

dsawczuk-int

Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.19 to 2.5.0. Release notes Sourced from urllib3's releases. 2.5.0 🚀 urllib3 is fundraising for HTTP/2 support urllib3 is raising ~$40,000 USD to release HTTP/2 support and...

dependabot[bot]

### Details: - *item1* - *...* ### Tickets: - *CVS-99737*

v-Golubev

EgorDuplensky

### Request Description We would like OpenVINO to add comprehensive support for Intel hardware acceleration within Microsoft's Azure Foundry Local platform. Currently, Azure Foundry Local supports various hardware accelerators (NVIDIA...

SRai22

### Details: - *item1* - *...* ### Tickets: - CVS-167319

alvoron

[GPU][TRANSFORMATIONS] RoPE fusion for GLM-4-9B Hugging Face

1

### Details: - Enabled RoPE op fusion for GLM-4-9B Hugging Face model on GPU to improve the performance - New config for RoPE is added to distinguish between mode that...

andrew-k-park

Added U2 precision parsers for compile_tool

1

### Details: - *Added `U2` precision parsers for **compile_tool** and other type parsers* ### Tickets:

AndreiFilipIntel

[NPUW] Make weights memory allocation sequential and ordered

3

smirnov-alexey