Home Knowledge Base QAT

QAT

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Gemma 4 QAT models: Optimizing compression for mobile and laptop efficiency

Gemma 4 QAT models: Optimizing model compression for mobile and laptop efficiency Since releasing Gemma 4 two months ago, we've been continuously working to expand its capabilities. First, we introduced Multi-Token Prediction (MTP) to accelerate inference, and just a couple of days ago, we released a 12B model to bridge the gap between our E4B and 26B MOE models. Today, we are releasing new checkpoints optimized with Quantization-Aware Training (QAT) to make Gemma 4 even more efficient, so...

Hacker News 5d ago

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

arXiv:2606.09012v1 Announce Type: new Abstract: Post-training quantization (PTQ) converts a trained full-precision model into low-bit weights without task-level retraining, while quantization-aware training (QAT) incorporates quantization into the training loop. Although PTQ is efficient and often accurate at moderate bitwidths, it can fail sharply at aggressive bitwidths; QAT is more expensive but can often recover the lost accuracy. We propose a unified geometric framework that explains...

arXiv CS 1d ago

Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training

arXiv:2605.25054v2 Announce Type: replace Abstract: Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing mixed-precision methods typically operate at coarse layer- or channel-level granularity. These methods often rely on heuristic or search-based bit-allocation strategies, which may overlook fine-grained variability...

arXiv CS 2d ago

Learning Quantized Continuous Controllers for Integer Hardware

arXiv:2511.07046v4 Announce Type: replace Abstract: Deploying continuous-control reinforcement learning policies on embedded hardware requires meeting tight latency and power budgets. Small FPGAs can deliver these, but only if costly floating-point pipelines are avoided. We study quantization-aware training (QAT) of policies for integer inference and we present a learning-to-hardware pipeline that automatically selects low-bit policies and synthesizes them to an Artix-7 FPGA.

arXiv CS 1d ago

Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition

Announce Type: replace Abstract: Large neural networks achieve state-of-the-art performance on many tasks, yet their sheer size hinders deployment on resource-constrained devices. Among existing compression approaches, cross-layer parameter sharing remains relatively unexplored for transformer models.

arXiv CS 8d ago

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

arXiv:2605.16138v2 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost. This gap is particularly large for FPGA deployment, where cost is dominated by a multi-dimensional budget of lookup tables, DSPs, flip-flops, BRAM, and latency. We present the Surrogate Neural Architecture...

arXiv CS 5d ago

MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

From the first roaring racer of the combustion age to the sonic boom that shattered the sound barrier, humanity's hunger for speed is written into our very DNA. The speed of AI reasoning is no different — it defines the boundaries of intelligence itself. When a model is fast enough, it ceases to be a tool you wait on and becomes an extension of your own thinking: responding in real time, iterating in an instant, collaborating without friction.

Hacker News 2d ago