https://community.intel.com/t5/Software-Tuning-Performance/Ultra-9-with-two-5080GPU-best-performance/m-p/1731688#M8601 <P><SPAN>Hello, we need direct personnel assistance at proffessional level for our understanding how to use Ultra9 with two 5080GPU efficiently, and to verify our workflow for best performance.</SPAN><BR /><SPAN>This support can be remotely/online/offline (chargeable basis also fine for us)</SPAN></P><P>&nbsp;</P><P><SPAN>Application:&nbsp;</SPAN></P><P><SPAN>1. Operating System version: Window 11 Pro 24H<BR />2. CPU model (Ultra 9 exact model): Intel core ultra 9 15th gen 285k<BR />3. GPU model(s) (e.g., RTX 5080 ×2): RTX 5080 16GB DDR7 X 2 Nos<BR />4. Motherboard: MSI MEG Z890 GODLIKE<BR />5. RAM: CV 32X2 RGB PRO 6000 MHZ32X2 kit<BR />6. SSD: Samsung 990 pro 1TB SSD<BR />7. Programming language and framework: Python 3.10; Cuda 12.9.0; Pytorch 2.8.0.Dev 2025+CU128; Torchaudio 2.6.0Dev; Torchvision 0.22.0; Ultralytics 8.3.137<BR />8. Type of workload: During Inference GPU usage reaching upto 20% only, other processing part CPU maximum 4 cores uage outof 24 core, (how to use multithreading and enable all core usage)</SPAN></P><P>&nbsp;</P><P>&nbsp;</P> Mon, 29 Dec 2025 06:44:59 GMT Avip008 2025-12-29T06:44:59Z https://community.intel.com/t5/Software-Tuning-Performance/Ultra-9-with-two-5080GPU-best-performance/m-p/1731688#M8601 <P><SPAN>Hello, we need direct personnel assistance at proffessional level for our understanding how to use Ultra9 with two 5080GPU efficiently, and to verify our workflow for best performance.</SPAN><BR /><SPAN>This support can be remotely/online/offline (chargeable basis also fine for us)</SPAN></P><P>&nbsp;</P><P><SPAN>Application:&nbsp;</SPAN></P><P><SPAN>1. Operating System version: Window 11 Pro 24H<BR />2. CPU model (Ultra 9 exact model): Intel core ultra 9 15th gen 285k<BR />3. GPU model(s) (e.g., RTX 5080 ×2): RTX 5080 16GB DDR7 X 2 Nos<BR />4. Motherboard: MSI MEG Z890 GODLIKE<BR />5. RAM: CV 32X2 RGB PRO 6000 MHZ32X2 kit<BR />6. SSD: Samsung 990 pro 1TB SSD<BR />7. Programming language and framework: Python 3.10; Cuda 12.9.0; Pytorch 2.8.0.Dev 2025+CU128; Torchaudio 2.6.0Dev; Torchvision 0.22.0; Ultralytics 8.3.137<BR />8. Type of workload: During Inference GPU usage reaching upto 20% only, other processing part CPU maximum 4 cores uage outof 24 core, (how to use multithreading and enable all core usage)</SPAN></P><P>&nbsp;</P><P>&nbsp;</P> Mon, 29 Dec 2025 06:44:59 GMT https://community.intel.com/t5/Software-Tuning-Performance/Ultra-9-with-two-5080GPU-best-performance/m-p/1731688#M8601 Avip008 2025-12-29T06:44:59Z