Search AI news

Search headlines, summaries and articles to connect the dots.

2026-11-09

arXiv cs.DC13:00

ISER-MoE: Dynamic In-Switch Replication of Hot Experts for Load Balancing in Expert-Parallel

arXiv:2611.09008v1 Announce Type: new Abstract: Expert-parallel mixture-of-experts (MoE) layers run at the pace of the most loaded GPU, and a few hot experts carry most of the excess load. Replicating them at every MoE layer balances the load only if their weights arrive within the layer, and broadcasting from the owner is the bottleneck: point-to-point copies overload it, and baseline broadcasts pay latency or bandwidth overheads. We present ISER-MoE (In-Switch Expert Replication for MoE), built in TensorRT-LLM, which multicasts hot experts through the NVLink switch to fixed GPU groups, so each byte leaves its owner once. A GPU scheduler assigns hot experts to groups per layer, and a multi-port broadcast spreads the injection over the group's ports, both overlapped with the shared expert. In trace replay, the scheduler removed 98-99% of the excess load; in prefill serving of DeepSeek-V4-Pro, throughput rose 17.4% on a math benchmark and 7.2% on agentic prompts.

2026-10-27

arXiv cs.DC12:00

When and Why to Use TMA: A Workload-Grounded Characterization of Tensor Memory Acceleration on NVIDIA Hopper GPUs

arXiv:2610.34907v1 Announce Type: new Abstract: The Tensor Memory Accelerator (TMA), introduced on NVIDIA Hopper, is used pervasively in production GPU kernels yet its usage is conspicuously selective: expert kernel developers in CUTLASS, FlashAttention-3, and FlashInfer apply TMA to some tensor operands within a kernel but fall back to cp.async, direct global loads, or distributed shared memory (DSM) for others. Vendor documentation describes the API, and recent microbenchmarking work characterizes TMA throughput in isolation, but neither answers the question practitioners actually face: given a memory operand in a kernel, should it use TMA, and if so, with or without cluster multicast? We address this gap with a workload-grounded characterization study on H100. We catalog the TMA, multic

Timeline and related coverage

2026-10-26

arXiv cs.CV12:00

DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model

arXiv:2610.31734v1 Announce Type: new Abstract: A live esports broadcast needs a director who chooses which camera goes on air and a caster who talks over that choice, every second and without knowing what comes next. Streaming video language models have learned to commentate, but only over a broadcast that a human director has already produced. We study live broadcast production, in which a model receives the raw camera of every player and must both direct and commentate from the past alone. We present DirCast, a single streaming video language model that does both. Every second it scans all cameras at low resolution, decides with a hold-or-switch director whether and where to cut, and reads the chosen camera at high resolution before it speaks. Its context keeps what went on air and what

Timeline and related coverage

arXiv cs.DC12:00

Quantum Cadence: Post-Quantum Consensus with Multiple Concurrent Proposers

arXiv:2610.32803v1 Announce Type: new Abstract: The consensus protocols of most high-performance blockchains use quorum certificates, which bundle the signatures of a quorum of validators. Signature schemes such as BLS can aggregate the signatures of a whole quorum into a single short signature, which keeps these certificates small. A large-scale quantum computer would break these schemes, and no post-quantum scheme with comparable aggregate size and aggregation time is known. Without aggregation, a certificate holds one large post-quantum signature per member of the quorum, so it becomes infeasible for each validator to broadcast certificates, as modern consensus protocols often require. We present Quantum Cadence, a post-quantum consensus protocol with multiple concurrent proposers that

Timeline and related coverage