From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

From Files to Chunks: Improving HF Storage Efficiency

LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data

arXiv:2607. 28880v1 Announce Type: cross Abstract: Modern multimedia machine learning workloads increasingly store large-scale datasets in cloud object storage services such as AWS S3.

MUFFLe: Efficient Model Update Compression via Generalized Deduplication for Federated Learning

arXiv:2606. 14354v1 Announce Type: new Abstract: Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates.

CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG under Document Isolation

arXiv:2606. 15179v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) has emerged as a pivotal technique for improving language models by incorporating external knowledge at inference time.

Introducing Storage Regions on the HF Hub

Announcing Evaluation on the Hub

Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot

MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments

arXiv:2606. 04171v1 Announce Type: cross Abstract: File-type classification underlies many workflows like malware triage, forensic carving, packet inspection, and storage indexing.

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving

arXiv:2607. 08930v1 Announce Type: new Abstract: Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency.

Streaming datasets: 100x More Efficient

RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving

arXiv:2609.07008v1 Announce Type: new Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it...

Towards Distributed Inference of LLMs on a P2P Network

arXiv:2606. 17059v1 Announce Type: cross Abstract: Prefix caching can reduce LLM inference latency by reusing KV caches across requests with shared prompts, but cluster-scale reuse is challenging because caches are partitioned across nodes.