Tag
This paper introduces Brevis, a lossless tensor compression method that formulates compression as program synthesis using a typed DSL. It achieves 33.93% storage reduction on public checkpoints and outperforms general-purpose and tensor-specific compressors.
The paper introduces MESH-FL, an entropy-guided matrix product state compression framework for multimodal federated learning on edge devices. It adaptively allocates compression ranks per layer and modality, achieving up to 56.8× compression and 2.01% final accuracy improvement over uncompressed FedAvg on a heterogeneous Raspberry Pi cluster.
0xSero has released new FP8 and NVFP4 quantized versions of the Tencent Hy3-preview model, enabling it to run on 256GB VRAM with full context.