🖥️ ML Systems - Bingran · Scour

Floating-point autotuning with customized precisions

📐Scaling Laws Academic

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

📐Scaling Laws Academic

BIDENT: Heterogeneous Operator-level Mapping for Efficient Edge Inference

📐Scaling Laws Academic

Communication Strategy Selection for Multi-GPU 3D FDTD with Convolutional Perfectly Matched Boundary Layers

📐Scaling Laws Academic

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving

💬LLMs Academic

StageFrontier: Synchronization-Aware Stage Accounting for Distributed ML Training

📉Deep Learning Academic

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control

📐Scaling Laws Academic

SABLE: GPU-Based Power Flow Accelerator for Sparsity-Aware Batched Learning

📉Deep Learning Academic

DeployBench: Benchmarking LLM Agents for Research Artifact Deployment

🤖AI Agents Academic

RhinoVLA Technical Report

📄arXiv Academic

Video-Rate Streaming Stylization on a Vision-Aware MLLM-Conditioned Edit Diffusion: Asymmetric Batched Inference on a Distilled UNet + MLLM Text Encoder

🔄Transformers Academic

No more posts from Bingran's subscribed feeds.

Scour all 25258 feeds Learn more about Feeds

Log in to enable infinite scrolling