Technical Report

Moreh-Tenstorrent AI Data Center Solution System Architecture
November 18, 2025

Moreh combine Tenstorrent’s lightweight and scalable hardware with our proprietary software stack to deliver an efficient and flexible solution for large-scale AI data centers.
21K Output Tokens Per Second DeepSeek Inference on AMD Instinct MI300X GPUs with Expert Parallelism
November 13, 2025

Moreh demonstrated that DeepSeek-R1 inference can be executed at a decoding throughput of >21,000 tokens/sec by implementing EP on the ROCm software stack.
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.