5 papers
DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs
Jiaxuan Chen, Jianshu She, Ye Yuan +5
LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a h…
FOLD: Fuzzy Online Deduplication for Very Large Evolving Datasets via Approximate Nearest Neighbor Search
Nelson Bore, Pritish Mishra, Constantin Adam +2
Fuzzy deduplication is key to constructing large language model training corpora. However, classic Locality-Sensitive Hashing (LSH) pipelines scale poorly as corpora grow and are i…
A Pragmatic Approach to Learned Indexing in RocksDB: Targeted Optimizations with Minimal System Modification
Shubham Vashisth, Olivier Michaud, Bettina Kemme +1
Learned indexes have emerged as a promising alternative to traditional index structures, offering higher throughput and lower memory usage by approximating the cumulative key distr…
MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing
Rahma Nouaji, Stella Bitchebe, Ricardo Macedo +1
Data loaders are used by Machine Learning (ML) frameworks like PyTorch and TensorFlow to apply transformations to data before feeding it into the accelerator. This operation is cal…
MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds
Stella Bitchebe, Oana Balmau
A large body of research has employed Machine Learning (ML) models to develop learned operating systems (OSes) and kernels. The latter dynamically adapts to the job load and dynami…