# On the Limitations of Non-GPU AI Accelerators for Large-Model Inference: A Field Study of MoE and Multimodal Serving on Huawei Ascend

arXiv: https://arxiv.org/abs/2607.08215 · HTML: https://mlsanity.com/paper/2607.08215/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)

## Abstract (arXiv)

Non-GPU AI accelerators are increasingly adopted as alternatives to general-purpose GPUs for large-model inference, but the real engineering cost of migrating demanding workloads beyond CUDA remains poorly documented. We present a field study of deploying two large inference workloads on a 16-device Huawei Ascend 910 system using CANN and vLLM-Ascend: an LLM-as-a-judge safety and alignment evaluation pipeline based on a W8A8 MoE judge model, DeepSeek-V4-Flash, and a multimodal medical vision--language benchmark based on DeepSeek-V4-Flash-Vision for MMMU and MMMU-Pro. Making these workloads reliable required twelve source-level patches to the vendor inference plugin, disabling several high-throughput features to preserve numerical correctness, and adding operational safeguards for recurring device-level failures. We summarize the main platform limitations in eight categories: incomplete operator and feature support, fragile parallelism, numerical faults in low-level kernels, immature graph compilation, unstable advanced features, limited scalability, weak observability, and ecosystem fragmentation. For each category, we report the symptoms, evidence, and likely causes. We also quantify the integration effort, concurrency behavior, and benchmark quality to show that both workloads were served correctly. Our study provides a reproducible reference for teams evaluating or operating non-GPU accelerators for large-model inference.