# The Inference Alpha: Maximizing Frontier Models on AMD

DevFeed: [The Inference Alpha: Maximizing Frontier Models on AMD](<https://devfeed.tech/articles/the-inference-alpha-maximizing-frontier-models-on-amd-19907.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/maximize-frontier-models>)

Author: Emilio Andere

Published: 2026-06-10T14:27:49Z

Content type: article

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [Inference Performance](<https://devfeed.tech/topics/inference-performance.md>), [cloud-infrastructure](<https://devfeed.tech/topics/cloud-infrastructure.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Optimization](<https://devfeed.tech/topics/optimization.md>), [systems](<https://devfeed.tech/topics/systems.md>), [Digital Ocean](<https://devfeed.tech/topics/digital-ocean.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [cost](<https://devfeed.tech/tags/cost.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [inference](<https://devfeed.tech/tags/inference.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [models](<https://devfeed.tech/tags/models.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [performance](<https://devfeed.tech/tags/performance.md>)

## AI overview

DigitalOcean describes engineering work to improve frontier LLM inference performance and cost-efficiency on AMD GPUs. It reports increasing Kimi 2.5 throughput from 22.5 to 255.2 tokens per second on a specified workload, an 11.33x speedup, and reports additional optimization work for DeepSeek V3.2.

## Source excerpt

At DigitalOcean, we're committed to providing high-performance infrastructure for the next generation of AI, which is why we've been focused on hosting frontier Large Language Models (LLMs) on frontier GPUs--including AMD GPUs. We see inference performance as an intricate systems-level challenge. For frontier open-weight models, achieving peak output speed is not just about the raw hardware. It also depends on a complex interaction between model architecture, runtime execution, memory systems, scheduling, and decoding strategy. We believe there's a significant "performance alpha" found in specialized inference engineering. Optimizing for both speed and cost-efficiency requires a much deeper approach than standard configuration sweeps. By taking a custom approach to the software stack, we can demonstrate that achieving performance parity with more expensive hardware is entirely possible. While the current software ecosystem often presents non-obvious hurdles, deep engineering allows us to deliver stronger inference economics on high-performance AMD infrastructure relative to conventional flagship deployments. The Proof is in the Throughput To ground our "Performance Alpha" theory in reality, DO worked with Wafer to achieve high performance on specific frontier models on AMD GPUs through various optimizations. By utilizing Wafer's Agent to identify inefficiencies and apply appropriate fixes, we were able to move beyond marginal gains toward order-of-magnitude improvements that change how these models are used in production.* Kimi 2.5 (High-Speed Single Stream) On a standard 10k input / 1.5k output workload, a stock configuration on 8x MI350X/MI355x hardware delivered a baseline of 22.5 tok/s. Through deep kernel optimization and a customized inference framework, we increased this to 255.2 tok/s - representing an 11.33x speedup with zero trade-offs in accuracy. DeepSeek V3.2 (Full-Stack Scaling) While stock frameworks achieved 38.5 tok/s for single-request output speed,