Lamini
Using Supermicro GPU Servers with the AMD Instinct™ MI300X, Lamini is able to offer LLM tuning at high speed.
Drive your business success with the right technology for all AI workloads
As the pace—and urgency—of AI innovation accelerates, Supermicro and AMD are working together to help you stay ahead. Deploy Supermicro rack-ready servers with AMD EPYC™ processors and AMD Instinct™ accelerators to unleash performance, cost-effectiveness, and scalability for the massive AI workloads of today and tomorrow.
Up to
1.64x
Faster
Conquer AI Challenges with GPU Acceleration
Together, Supermicro and AMD offer an open, robust ecosystem and the breakthrough power needed for the AI lifecycle—all with leadership performance and efficiency to meet your unique needs.
AMD EPYC processors can be used for small-scale AI models and workloads where proximity to data matters, while AMD Instinct accelerators shine for large models and dedicated AI deployments demanding very high performance. Compared to the Nvidia H100 HGX, the AMD Instinct Platform can offer a throughput increase of up to 1.6x when running inference on LLMs like BLOOM 176B.1
Evolve for AI with Ease
Discover how Supermicro H13 servers, powered by AMD Instinct M1300X accelerators, streamline deployments at scale for the largest AI models.
Level Up Performance with CPU/GPU Integration
Explore how Supermicro H13 systems, powered by AMD Instinct M1300A APUs, combine the power of AMD Instinct accelerators and AMD EPYC processors with shared memory to supercharge your AI initiatives.
Note: Test results for white box system; please refer to www.supermicro.com/aplus for Supermicro product/platform information.
Modernize and Make Room for AI
To make the most of IT budgets, many data centers are already pushing the limits of available space, power, or both. Supermicro servers with AMD EPYC processors deliver the leadership performance and efficiency to consolidate your core workloads—freeing up space, power, and cooling to support new business-critical AI workloads.
Replace 100 old 2P Intel® Xeon® Platinum 8280 CPU-based servers with 14 new AMD EPYC 9965 CPU-based servers2
Up to 87% fewer servers
Up to 71% less power
Up to 67% lower 3-yr TCO
Help lower cost and TCO AMD EPYC 9965 CPU-based servers vs Intel® Xeon® Platinum 8592+ CPU-based servers2
Up to 63% fewer servers
Up to 45% less power
Up to 44% lower 3-yr TCO
Note: Test results for white box system; please refer to www.supermicro.com/aplus for Supermicro product/platform information.
Why Modernize Now? The IDC Perspective
Learn how AI is driving demand for richly configured servers—and why IDC says it’s imperative to adopt a modern technology stack now.
AMD and Supermicro Make Light Work of Heavy Inference
Experience for yourself when you test-drive your AI workloads by requesting a trial of Supermicro H14 servers powered by AMD EPYC processors.
Customer Stories
Resources
Newsletter and Request Contact
Subscribe to Data Center Insights from AMD
Request Contact from an AMD EPYC™ and Supermicro Sales Expert
Footnotes
- MI300-34: Token generation throughput using DeepSpeed Inference with the Bloom-176b model with an input sequence length of 1948 tokens, and output sequence length of 100 tokens, and a batch size tuned to yield the highest throughput on each system comparison based on AMD internal testing using custom docker container for each system as of 11/17/2023.
Configurations:
2P Intel Xeon Platinum 8480C CPU powered server with 8x AMD Instinct™ MI300X 192GB 750W GPUs, pre-release build of ROCm™ 6.0, Ubuntu 22.04.2.
Vs.
An Nvidia DGX H100 with 2x Intel Xeon Platinum 8480CL Processors, 8x Nvidia H100 80GB 700W GPUs, CUDA 12.0, Ubuntu 22.04.3.
8 GPUs on each system were used in this test.
Server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers and optimizations.
- 9xx5TCO-001B: This scenario contains many assumptions and estimates and, while based on AMD internal research and best approximations, should be considered an example for information purposes only, and not used as a basis for decision making over actual testing. The AMD Server & Greenhouse Gas Emissions TCO (total cost of ownership) Estimator Tool - version 1.12, compares the selected AMD EPYC™ and Intel® Xeon® CPU based server solutions required to deliver a TOTAL_PERFORMANCE of 39100 units of SPECrate2017_int_base performance as of October 10, 2024. This scenario compares a legacy 2P Intel Xeon 28 core Platinum_8280 based server with a score of 391 versus 2P EPYC 9965 (192C) powered server with an score of 3000 (https://www.spec.org/cpu2017/results/res2024q4/cpu2017-20240923-44837.pdf) along with a comparison upgrade to a 2P Intel Xeon Platinum 8592+ (64C) based server with a score of 1130 (https://spec.org/cpu2017/results/res2024q3/cpu2017-20240701-43948.pdf). Actual SPECrate®2017_int_base score for 2P EPYC 9965 will vary based on OEM publications. Environmental impact estimates made leveraging this data, using the Country / Region specific electricity factors from the 2024 International Country Specific Electricity Factors 10 – July 2024, and the United States Environmental Protection Agency 'Greenhouse Gas Equivalencies Calculator'.
Footnotes
- MI300-34: Token generation throughput using DeepSpeed Inference with the Bloom-176b model with an input sequence length of 1948 tokens, and output sequence length of 100 tokens, and a batch size tuned to yield the highest throughput on each system comparison based on AMD internal testing using custom docker container for each system as of 11/17/2023.
Configurations:
2P Intel Xeon Platinum 8480C CPU powered server with 8x AMD Instinct™ MI300X 192GB 750W GPUs, pre-release build of ROCm™ 6.0, Ubuntu 22.04.2.
Vs.
An Nvidia DGX H100 with 2x Intel Xeon Platinum 8480CL Processors, 8x Nvidia H100 80GB 700W GPUs, CUDA 12.0, Ubuntu 22.04.3.
8 GPUs on each system were used in this test.
Server manufacturers may vary configurations, yielding different results. Performance may vary based on use of latest drivers and optimizations. - 9xx5TCO-001B: This scenario contains many assumptions and estimates and, while based on AMD internal research and best approximations, should be considered an example for information purposes only, and not used as a basis for decision making over actual testing. The AMD Server & Greenhouse Gas Emissions TCO (total cost of ownership) Estimator Tool - version 1.12, compares the selected AMD EPYC™ and Intel® Xeon® CPU based server solutions required to deliver a TOTAL_PERFORMANCE of 39100 units of SPECrate2017_int_base performance as of October 10, 2024. This scenario compares a legacy 2P Intel Xeon 28 core Platinum_8280 based server with a score of 391 versus 2P EPYC 9965 (192C) powered server with an score of 3000 (https://www.spec.org/cpu2017/results/res2024q4/cpu2017-20240923-44837.pdf) along with a comparison upgrade to a 2P Intel Xeon Platinum 8592+ (64C) based server with a score of 1130 (https://spec.org/cpu2017/results/res2024q3/cpu2017-20240701-43948.pdf). Actual SPECrate®2017_int_base score for 2P EPYC 9965 will vary based on OEM publications. Environmental impact estimates made leveraging this data, using the Country / Region specific electricity factors from the 2024 International Country Specific Electricity Factors 10 – July 2024, and the United States Environmental Protection Agency 'Greenhouse Gas Equivalencies Calculator'.