arXiv AI August 21, 2026 By Jiahao Lin, Alish Kanani, Sangwan Lee, Jaehyun Park, Umit Ogras

HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads

arXiv:2608. 19395v1 Announce Type: cross Abstract: Hybrid Transformer-Mamba large language models (LLMs) enhance long-context efficiency, but their heterogeneous computation and communication patterns complicate efficient hardware acceleration.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 16

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems

arXiv:2604. 26963v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators.

By Yifei Wang, Hancheng Ye, Yechen Xu, Cong Guo, Chiyue Wei, Qinsi Wang, Dongting Li, Tingjun Chen, Hai "Helen" Li, Danyang Zhuo, Yiran Chen

llms agents efficiency

arXiv AI

Jul 7

Data Driven Optimization of GPU efficiency for Distributed LLM-Adapter Serving

arXiv:2602. 24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.

By Ferran Agullo, Joan Oliveras, Chen Wang, Alberto Gutierrez-Torre, Olivier Tardieu, Alaa Youssef, Jordi Torres, Josep Ll. Berral

llms efficiency benchmarks

arXiv Machine Learning

2d ago

DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling

arXiv:2605.21603v1 Announce Type: cross Abstract: Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different r...

By Yi Pan, Yile Gu, Jinbin Luo, Yibo Wu, Ziren Wang, Hongtao Zhang, Ziyi Xu, Shengkai Lin, Baris Kasikci, Stephanie Wang

efficiency benchmarks

arXiv AI

Jul 14

HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference

arXiv:2607. 11586v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded.

By Yongqin Zhang

llms

arXiv AI

Jul 21

ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts

arXiv:2607. 17074v1 Announce Type: cross Abstract: Mixture of Experts (MoE) architectures have emerged as a dominant paradigm for scaling Large Language Models (LLMs).

By Pratyush Dhingra, Pramit Kumar Pal, Janardhan Rao Doppa, Partha Pratim Pande

llms benchmarks

arXiv AI

Jun 3

E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments

arXiv:2606. 03770v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become integral to modern applications, yet their deployment remains challenging.

By Truong-Thanh Le, Amir Taherkordi, Hoang-Loc La, Frank Eliassen, Phuong Hoai Ha, Peiyuan Guan

llms

One email a morning, machine-written

Related stories

MARS: Efficient, Adaptive Co-Scheduling for Heterogeneous Agentic Systems

Data Driven Optimization of GPU efficiency for Distributed LLM-Adapter Serving

DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling

HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference

ThAME: 3D Memory-Enabled Heterogeneous Accelerator for LLM Mixture of Experts

E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments