Deformable transformers deliver state-of-the-art detection but map poorly to hardware due to irregular memory access and low arithmetic intensity. We introduce QUILL, a schedule-aware accelerator that turns deformable attention into cache-friendly, single-pass work. At its core, Distance-based Out-of-Order Querying (DOOQ) orders queries by spatial proximity; the look-ahead drives a region prefetch into an alternate buffer--forming a schedule-aware prefetch loop that overlaps memory and compute. A fused MSDeformAttn engine executes interpolation, Softmax, aggregation, and the final projection (W''m) in one pass without spilling intermediates, while small tensors are kept on-chip and surrounding dense layers run on integrated GEMMs. Implemented as RTL and evaluated end-to-end, QUILL achieves up to 7.29x higher throughput and 47.3x better energy efficiency than an RTX 4090, and exceeds prior accelerators by 3.26-9.82x in throughput and 2.01-6.07x in energy efficiency. With mixed-precision quantization, accuracy tracks FP32 within <=0.9 AP across Deformable and Sparse DETR variants. By converting sparsity into locality--and locality into utilization--QUILL delivers consistent, end-to-end speedups.

Approximate nearest-neighbor search (ANNS) algorithms have become increasingly critical for recent AI applications, particularly in retrieval-augmented generation (RAG) and agent-based LLM applications. In this paper, we present CRINN, a new paradigm for ANNS algorithms. CRINN treats ANNS optimization as a reinforcement learning problem where execution speed serves as the reward signal. This approach enables the automatic generation of progressively faster ANNS implementations while maintaining accuracy constraints. Our experimental evaluation demonstrates CRINN's effectiveness across six widely-used NNS benchmark datasets. When compared against state-of-the-art open-source ANNS algorithms, CRINN achieves best performance on three of them (GIST-960-Euclidean, MNIST-784-Euclidean, and GloVe-25-angular), and tied for first place on two of them (SIFT-128-Euclidean and GloVe-25-angular). The implications of CRINN's success reach well beyond ANNS optimization: It validates that LLMs augmented with reinforcement learning can function as an effective tool for automating sophisticated algorithmic optimizations that demand specialized knowledge and labor-intensive manual refinement. Code can be found at https://github.com/deepreinforce-ai/CRINN

Personalized recommendation is a ubiquitous application on the internet, with many industries and hyperscalers extensively leveraging Deep Learning Recommendation Models (DLRMs) for their personalization needs (like ad serving or movie suggestions). With growing model and dataset sizes pushing computation and memory requirements, GPUs are being increasingly preferred for executing DLRM inference. However, serving newer DLRMs, while meeting acceptable latencies, continues to remain challenging, making traditional deployments increasingly more GPU-hungry, resulting in higher inference serving costs. In this paper, we show that the embedding stage continues to be the primary bottleneck in the GPU inference pipeline, leading up to a 3.2x embedding-only performance slowdown. To thoroughly grasp the problem, we conduct a detailed microarchitecture characterization and highlight the presence of low occupancy in the standard embedding kernels. By leveraging direct compiler optimizations, we achieve optimal occupancy, pushing the performance by up to 53%. Yet, long memory latency stalls continue to exist. To tackle this challenge, we propose specialized plug-and-play-based software prefetching and L2 pinning techniques, which help in hiding and decreasing the latencies. Further, we propose combining them, as they complement each other. Experimental evaluations using A100 GPUs with large models and datasets show that our proposed techniques improve performance by up to 103% for the embedding stage, and up to 77% for the overall DLRM inference pipeline.

The promising applications of large language models are often constrained by the limited GPU memory capacity available on edge devices. Mixture-of-Experts (MoE) models help mitigate this issue by activating only a subset of the model's parameters during computation, allowing the unused parameters to be offloaded to host memory and reducing overall GPU memory demand. However, existing cache-based offloading solutions handle cache misses reactively and significantly impact system performance. In this paper, we propose ProMoE, a novel proactive caching system that leverages intermediate model results to predict subsequent parameter usage. By proactively fetching experts in advance, ProMoE removes the loading time from the critical path and diminishes the performance overhead of offloading. Our evaluations demonstrate that ProMoE achieves an average speedup of 2.13x and 2.84x in the prefill and decode stages respectively, compared to existing offloading solutions.

Streaming Automatic Speech Recognition (ASR) in voice assistants can utilize prefetching to partially hide the latency of response generation. Prefetching involves passing a preliminary ASR hypothesis to downstream systems in order to prefetch and cache a response. If the final ASR hypothesis after endpoint detection matches the preliminary one, the cached response can be delivered to the user, thus saving latency. In this paper, we extend this idea by introducing predictive automatic speech recognition, where we predict the full utterance from a partially observed utterance, and prefetch the response based on the predicted utterance. We introduce two personalization approaches and investigate the tradeoff between potential latency gains from successful predictions and the cost increase from failed predictions. We evaluate our methods on an internal voice assistant dataset as well as the public SLURP dataset.

Before we see how the tf.data API works, let's review how we usually train a Keras model. First, we need a dataset. An example is the fashion MNIST dataset that comes with the Keras API, which we have 60,000 training samples and 10,000 test samples of 28 28 pixels in grayscale and the corresponding classification label is encoded with integers 0 to 9. The dataset is a NumPy array. Then we can build a Keras model for classification, and with the model's fit() function, we provide the NumPy array as data.