arXiv (All)
open access
SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference
Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D) expert transfers enter the critical path of decoding. Speculative decoding verifies several draft tokens in one forward pass, yet in an MoE model ea
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware#798975
- WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware#797561
- The Limits of Speculation: Bounding Speculative Decoding in Mixture-of-Experts#1036839
- AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters#1257979
- Mentored Decoding: Faster Inference meets Boosting#1104673
Record · ID 1326667
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive