11 papers
Language-Specific Gaps in AI Safety Training Datasets
Chialuka Prisca-Mary Onuoha, Bright Etornam Sunu, Rashidat Sikiru
Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking user…
HiSparse: Scaling Sparse-Attention Decoding with Hierarchical KV Cache Management
Zhiqiang Xie, Zhangheng Huang, Tingwei Huang +3
Top-k sparse attention makes long-context LLM decoding cheap to compute: each step reads only a few thousand selected KV entries rather than the full context. Serving systems, howe…
Eiger: An Efficient Library for GPU-based Data Analytics
Bowen Wu, Marko KabiÄ, Sven Hepkema +3
GPUs have become an increasingly attractive platform for accelerating analytical workloads due to their massive parallelism and high memory bandwidth. Recent studies show that in s…
ROSA: A Robotics Foundation Model Serving System for Robot Factories
Wenqi Jiang, Jason Clemons, Rowland O'Flaherty +5
Robotics foundation models (RFMs) are making general-purpose robots increasingly practical for factory deployments. While RFM serving systems are central to this vision, existing s…
Regulating Branch Parallelism in LLM Serving
Swapnil Gandhi, Siva Hari, William J. Dally +1
Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or und…
Sparse Checkpointing for Fast and Reliable MoE Training
Swapnil Gandhi, Christos Kozyrakis
As large language models scale, training them requires thousands of GPUs over extended durations--making frequent failures an inevitable reality. While checkpointing remains the pr…