Product
Solutions
Infrastructure
AMD GPU Appliance
Deploy fully integrated AMD GPU-based cluster systems with scalable RoCE networking

Tenstorrent Appliance
Deliver the lowest TCO with inherently scalable, network-integrated chips

Use Cases
End-to-End Model Deployment
Build cost-effective inference endpoints on-premises or in the cloud

Large Scale Training
Maximize GPU utilization and reduce training costs at the 1,000+ GPU scale

Operation
GPU Virtualization
Flexible GPU aggregation, decomposition, and scaling with heterogeneous GPU support

System Reliability
Automatic GPU failover and diagnostic hardware monitoring
Resources
Career
Company

moreh-vllm-performance-evaluation

Moreh vLLM Performance Evaluation: Llama 3.3 70B on AMD Instinct MI300X GPUs
August 30, 2025

Moreh vLLM achieves 1.68x higher output TPS, 2.02x lower TTFT, and 1.59x lower TPOT compared to the original vLLM for Meta's Llama 3.3 70B model.
Moreh vLLM Performance Evaluation: DeepSeek V3/R1 671B on AMD Instinct MI300X GPUs
August 29, 2025

Moreh vLLM achieves 1.68x higher output TPS, 1.75x lower TTFT, and 1.70x lower TPOT compared to the original vLLM for the DeepSeek V3/R1 671B model.