3 papers
cs.LG2026
Measuring and Reducing WebGPU Dispatch Overhead for LLM Inference
Jędrzej Maczan
Large Language Models are deployed to multiple types of environments, from internet browsers to edge devices, and WebGPU serves as a modern cross-platform standard. The engines for…
cs.LG2026
"As a Language Model...": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It
Jędrzej Maczan
Large Language Models (LLMs) tend to add disclaimers like "I'm just an AI" when asked about something related to themselves. The self-reports from such responses are used in debate…
cs.LG2026
Memory-Efficient Activation Checkpointing with Sliding Window and Hirschberg's Algorithm for 0/1 Knapsack Solving in PyTorch
Jędrzej Maczan
Activation checkpointing minimizes the runtime of neural networks under a given memory budget, by selecting which intermediate tensors to store and which to recompute. PyTorch solv…