NVIDIA L40S GPU-accelerated OCI Instances

Expanding NVIDIA GPU-Accelerated Instances for AI, Digital Twins, and Other Uses is Oracle Cloud Infrastructure

[{"selector":"#anim-790edc71-7758-4710-b243-da493ae18442 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(-16.60561646420807%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-9e363843-7a45-4bdf-ad20-aec6f7317d47","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}]

Businesses are quickly using generative AI, large language models (LLMs), sophisticated visuals, and digital twins

[{"selector":"#anim-36a82be7-779c-4237-813e-abac7418225c [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-35.234374910402764%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-b55bddea-06a9-4081-947c-268c7649a97e","keyframes":{"transform":["translate3d(-115.18988%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-eb79e7c5-db7b-4786-9cfc-685d9c5f0504","keyframes":{"transform":["rotateZ(-180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

Virtual machine powered by a single NVIDIA H100 Tensor Core GPU and the availability of NVIDIA L40S GPU bare-metal instances

[{"selector":"#anim-2fd4bfc1-0444-4277-91d3-59577eb91bdc [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(30.945312384376894%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-f239a1a3-bf31-4a1d-97a7-204b9997bb23","keyframes":{"transform":["translate3d(-115.18988%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-5a8c3dd3-1e7c-40b7-b16b-5b09fc4230bd","keyframes":{"transform":["rotateZ(-180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

The universal data centre GPU NVIDIA L40S has revolutionary multi-workload acceleration for generative AI, graphics, and video applications

[{"selector":"#anim-36b28dd0-c8d5-4acc-94de-26a2d36a4f66","keyframes":[{"offset":0,"transform":"translate3d(0, -179.10403%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.29,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.45,"transform":"translate3d(0, -50.364053236%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.61,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.71,"transform":"translate3d(0, -17.122345268%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.8,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.85,"transform":"translate3d(0, -6.429834677%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.92,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.96,"transform":"translate3d(0, -2.794022868%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":1,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"}],"delay":0,"duration":600,"fill":"both"}] [{"selector":"#anim-1a51a21f-c68f-4bf5-a44b-4ed1ee18415e [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(28.90624987200394%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}]

For Llama 3 8B with NVIDIA TensorRT-LLM at an input and output sequence length of 128, for instance, a single L40S GPU

[{"selector":"#anim-05b14316-49a8-458d-a4d6-332271eeecf1","keyframes":{"transform":["translate3d(120.52980%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-ccd0c631-9ac7-46cf-8a1e-5c6bd676cbde","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-6be375cc-d82a-4ddb-9f6e-3970bea645fc","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}] [{"selector":"#anim-f7528b53-d696-4881-856d-948cba38841b [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-21.874999829338588%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}]

The GPU is perfect for creating apps on the NVIDIA Omniverse platform, which enables AI-enabled digital twins and real-time, lifelike 3D simulations

[{"selector":"#anim-1677ef3e-1569-415d-822e-7893200c3c3c [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(-17.235056086276842%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-a502de1d-dd0a-4620-8f5b-b901e6221cb7","keyframes":{"transform":["translate3d(-116.32654%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-b80332f7-18ac-4853-8fc3-9c06d26e3f29","keyframes":{"opacity":[0,1]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"both"}] [{"selector":"#anim-42200dbb-2130-4d5a-a8d7-f27c6c7b83cf","keyframes":{"transform":["scale(0.15)","scale(1)"]},"delay":0,"duration":600,"easing":"cubic-bezier(0.4, 0.4, 0.0, 1)","fill":"forwards"}]

It supports AI tasks with 13 4th Gen Intel Xeon processor cores, 246GB system memory, and 2x 3.4TB NVMe SSDs

[{"selector":"#anim-1b20ef71-e118-45d6-87fa-c83279f1e2c0 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(3.4327402273326686%, 0, 0)","translate3d(0%, 0, 0)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-39daa38f-637b-4ee2-9d8f-3392e365b6de","keyframes":[{"offset":0,"transform":"translate3d(0, -225.33182%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.29,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.45,"transform":"translate3d(0, -63.363307784%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.61,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.71,"transform":"translate3d(0, -21.541721992%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.8,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.85,"transform":"translate3d(0, -8.089412338%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.92,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.96,"transform":"translate3d(0, -3.515176392%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":1,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"}],"delay":0,"duration":600,"fill":"both"}]

Oracle Cloud’s bare-metal compute with NVIDIA H100 and A100 GPUs, low-latency Supercluster

[{"selector":"#anim-63b95c50-ba0f-4735-9675-d66e769f6496 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate3d(-21.685267982563275%, 0, 0) translate(-25%, 0%) scale(1.5)","translate3d(0%, 0, 0) translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"fill":"forwards"}] [{"selector":"#anim-7d141035-5c3f-444a-a418-90af6ad19fc0","keyframes":{"transform":["translate3d(123.80952%, 0px, 0)","translate3d(0px, 0px, 0)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .8, 1)","fill":"both"}] [{"selector":"#anim-9093f7d9-b15f-477b-8ae3-89a427cf8664","keyframes":{"transform":["rotateZ(180deg)","rotateZ(0deg)"]},"delay":0,"duration":1000,"easing":"cubic-bezier(.2, 0, .5, 1)","fill":"forwards"}]

It has the NVIDIA Grace Hopper Superchip and NVLink-C2C, which connects the NVIDIA Grace CPU and NVIDIA Hopper GPU at 900GB/s

[{"selector":"#anim-92351e5b-35b1-45a9-9683-633711d1fc76 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(0%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-66481ba4-1c2d-4223-b493-c46454aafe52","keyframes":{"opacity":[0,1]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"both"}] [{"selector":"#anim-ce86c67c-cd73-4a54-b33a-d0ccb6b25f42","keyframes":{"transform":["scale(0.3333333333333333)","scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}]

This GPU can be used for a variety of high-performance applications, including media acceleration, large language model (LLM) training For more details govindhtech.com

[{"selector":"#anim-79cf71e4-ea55-4fed-987f-b4eca2e6ca72 [data-leaf-element=\"true\"]","keyframes":{"transform":["translate(-3.552713678800501e-15%, 0%) scale(1.5)","translate(0%, 0%) scale(1)"]},"delay":0,"duration":2000,"easing":"cubic-bezier(.3,0,.55,1)","fill":"forwards"}] [{"selector":"#anim-aaf35bb6-883a-462f-8345-9465543455dc","keyframes":[{"offset":0,"transform":"translate3d(0, -143.27136%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.29,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.45,"transform":"translate3d(0, -40.287906432%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.61,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.71,"transform":"translate3d(0, -13.696742016%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.8,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.85,"transform":"translate3d(0, -5.143441824%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":0.92,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"},{"offset":0.96,"transform":"translate3d(0, -2.2350332159999997%, 0)","easing":"cubic-bezier(.5, 0, 1, 1)"},{"offset":1,"transform":"translate3d(0, 0%, 0)","easing":"cubic-bezier(0, 0, .5, 1)"}],"delay":0,"duration":600,"fill":"both"}]