Launch-Bound and Substitutable: Why Three Inference Optimizations Fail to Pay Off in Mixture-of-Experts Models

[2608.26612] Launch-Bound and Substitutable: Why Three Inference Optimizations Fail to Pay Off in Mixture-of-Experts Models Skip to main content Search Submit Donate Log in Computer Science > Performance arXiv:2608.26612 (cs) [Submitted on 27 Aug 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: Launch-Bound and Substitutable: Why Three Inference Optimizations Fail to Pay Off in Mixture-of-Experts Models Authors: Gokulakannan Sakthivel , Jerry Wu , Amogh Rajendra , Giriprasad Radhakrishnan View PDF HTML (experimental) Abstract: Mixture-of-Experts (MoE) models route each token to a few of many expert networks, and that routing is data-dependent in a way standard inference optimizations do not expect. This paper measures what three of them actually deliver on OLMoE-1B-7B, DeepSeek-V2-Lite, and Qwen3-30B-A3B. Fused Triton kernels reach 5.6x to 9.0x in isolation but 0.999x end to end against a measured 1.07x ceiling, because the model spends its time waiting on roughly a thousand kernel launches per forward pass rather than on the arithmetic those kernels improve. INT4 quantization changes on average 0.53 of the eight selected experts per token position, yet replaying exactly those changed routes through full-precision weights reproduces only 2.7% of the quality loss, which makes the experts substitutable rather than specialized. Removing all 23 graph breaks from PyTorch's compiler, the step prior work treats as the structural fix, makes the model three times slower. A fourth result ties the three together: leaving the routers in FP16 lowers drift by 20% while raising loss, so routing fidelity and output quality are separable objectives. Every number recomputes from committed per-token route dumps. Subjects: Performance (cs.PF) Cite as: arXiv:2608.26612 [cs.PF] (or arXiv:2608.26612v2 [cs.PF] for this version) https://doi.org/10.48550/arXiv.2608.26612 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Gokulakannan Sakthivel [ view email ] [v1] Thu, 27 Aug 2026 04:51:07 UTC (45 KB) [v2] Fri, 28 Aug 2026 02:12:23 UTC (45 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.PF < prev | next > new | recent | 2026-08 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Launch-Bound and Substitutable: Why Three Inference Optimizations Fail to Pay Off in Mixture-of-Experts Models#779380
• Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization#1160986
• Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization#1155493
• FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving#998172
• OrderMoE: An expert similarity driven distributed edge MoE inference#386805