verifiedhigh · 0.85updated 2026-10-03

LMDeploy Accelerates Mixed-Precision LLM Inference with TurboMind (EuroSys 2027)

paper

Fields

sources/niche-lmdeploy-turbomind-paper

URL

https://arxiv.org/abs/2508.15601

Publisher

arXiv

Kind

paper

Published

2025-08-21

Accessed

2026-10-03

notes

TurboMind system paper, cited by the LMDeploy README as accepted to EuroSys 2027. Primary source behind the mixed-precision and MXFP4 claims in that README.

Notes

TurboMind system paper, cited by the LMDeploy README as accepted to EuroSys 2027. Primary source behind the mixed-precision and MXFP4 claims in that README.

Cross-references

This record references no other records.