OpenVINO 2024.4 Prepares For Core Ultra Series 2, New Gen AI Models
([Intel] 3 Hours Ago
OpenVINO 2024.4)
- Reference: 0001492575
- News link: https://www.phoronix.com/news/OpenVINO-2024.4
- Source link:
Intel engineers today released OpenVINO 2024.4 as the newest version of their open-source AI toolkit. OpenVINO 2024.4 prepares for upcoming Intel Core Ultra Series 2 "Lunar Lake" processors, supports newer Gen AI models, now supports Python 3.12, and finally adds official support for Red Hat Enterprise Linux 9.
OpenVINO 2024.4 adds support for the GLM-4-9B Chat, MiniCPM-1B, Llama 3 and 3.1, Phi-3-Mini, Phi-3-Medium and YOLOX-s models.
OpenVINO 2024.4 also expands its large language model (LLM) support with run-time optimizations for Xe Matrix Extensions (XMX) systolic arrays, memory sharing for Lunar Lake CPUs, a new PagedAttention feature for discrete GPUs, production-quality support for the OpenAI-compatible API, improved performance and memory consumption, Python 3.12 support, and support for RHEL9.
Downloads and more details on the new OpenVINO 2024.4 AI toolkit release via [1]GitHub .
[1] https://github.com/openvinotoolkit/openvino/releases/tag/2024.4.0
OpenVINO 2024.4 adds support for the GLM-4-9B Chat, MiniCPM-1B, Llama 3 and 3.1, Phi-3-Mini, Phi-3-Medium and YOLOX-s models.
OpenVINO 2024.4 also expands its large language model (LLM) support with run-time optimizations for Xe Matrix Extensions (XMX) systolic arrays, memory sharing for Lunar Lake CPUs, a new PagedAttention feature for discrete GPUs, production-quality support for the OpenAI-compatible API, improved performance and memory consumption, Python 3.12 support, and support for RHEL9.
Downloads and more details on the new OpenVINO 2024.4 AI toolkit release via [1]GitHub .
[1] https://github.com/openvinotoolkit/openvino/releases/tag/2024.4.0
phoronix