tensorrt
PulseAugur coverage of tensorrt — every cluster mentioning tensorrt across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
Ollama v0.32.6 boosts Qwen 3.5 speed on Apple Silicon, improves OpenAI compatibility · 4 sources tracked
Ollama has released version 0.32.6, significantly improving the performance of the Qwen 3.5 model on Apple Silicon Macs through the MLX engine and speculative decoding. This update also enhances compatibility with OpenA…
-
PixOOD pipeline optimized for real-time anomaly segmentation in autonomous vehicles
Researchers have developed an efficient anomaly segmentation pipeline called PixOOD, designed for real-time deployment on embedded hardware in autonomous vehicles and railway systems. This new approach optimizes the Ney…
-
Lightweight AI model identifies raptor species for wind turbine safety
Researchers have developed a lightweight image classification system for identifying raptor species on edge devices, specifically for wind turbine collision mitigation. The system utilizes knowledge distillation to trai…
-
NVIDIA TensorRT adds build monitoring and cancellation features
NVIDIA has introduced new capabilities for its TensorRT engine, allowing users to monitor and cancel long-running engine builds directly through Python or C++ interfaces. This enhancement provides greater control over l…
-
NanoVSR: Real-time video super-resolution for edge devices unveiled
Researchers have developed NanoVSR, a new video super-resolution architecture optimized for edge devices. This fully convolutional model uses structural reparameterization to achieve compatibility with hardware accelera…
-
Benchmarking edge inference frameworks for industrial machine vision · 2 sources tracked
A new research paper benchmarks the performance of four popular frameworks—PyTorch, ONNX Runtime, OpenVINO, and TensorRT—for deep learning inference on edge devices in industrial machine vision. The study found that Ope…
-
New models enhance robot manipulation by integrating vision and state
Researchers have developed several new methods to improve robot manipulation capabilities by better integrating visual information with the robot's state and actions. GeoProp, for instance, is a lightweight adapter that…
-
Transformer model enhances security for autonomous vehicle platoons
Researchers have developed AIMformer, a transformer-based framework designed for real-time detection of misbehavior in vehicular platoons. This system utilizes multi-head self-attention to analyze temporal dynamics with…
-
New RAMS system adapts YOLOv8 tiers for edge AI perception
Researchers have developed RAMS, a novel runtime controller designed for embedded edge perception systems. RAMS dynamically switches between different tiers of YOLOv8 models based on real-time device resource monitoring…
-
NVIDIA launches Halos OS for certified robotaxi safety
NVIDIA has introduced the Halos Operating System (OS) to enhance safety in autonomous vehicles, particularly for robotaxis. This new OS, built on the NVIDIA DRIVE Hyperion platform, provides a certified foundation for A…
-
LogNEO framework uses GPT-Neo for real-time log anomaly detection
Researchers have developed LogNEO, a new framework for detecting anomalies in system logs using EleutherAI's GPT-Neo model. This system employs a novel reinforcement learning approach with a position-aware reward scheme…
-
Together AI builds world's fastest speech-to-text stack
Together AI has developed a highly efficient speech-to-text system, significantly outperforming existing models in speed. Their approach addresses the unique challenges of audio data processing, which is substantially l…
-
New framework tackles industrial Edge AI deployment challenges
This paper introduces a new systems framework designed to improve the deployment of Edge AI applications on industrial embedded platforms. It argues that treating AI deployment as a systems problem, rather than just a m…
-
DEMON engine enables real-time diffusion control as musical instrument
Researchers have developed DEMON, a real-time diffusion engine that allows users to control the denoising process like a musical instrument. This system enables live performance adjustments to various parameters, achiev…
-
AI video inference sped up 3x by optimizing pipeline, not model
Researchers have developed a method to significantly accelerate video inference for computer vision models without altering the model itself. By optimizing the pipeline of frame reading, model inference, and result visu…
-
New framework optimizes LLM inference energy use on multi-GPU systems
Researchers have developed EnergyLens, a framework designed to optimize the energy consumption of large language models (LLMs) during inference on multi-GPU systems. This tool addresses the challenge of predicting and r…
-
New satellite system uses AI for real-time wildfire detection under strict constraints
Researchers have developed a real-time wildfire detection system for use on satellites, designed to operate under strict on-board constraints. The system utilizes a lightweight dense representation learning approach, sp…
-
New DEEP-GAP study compares NVIDIA T4 and L4 GPU inference performance
A new research paper introduces DEEP-GAP, a methodology for evaluating GPU inference performance. The study systematically compares the NVIDIA T4 and L4 GPUs using various deep learning models and precision modes. Resul…
-
AI models advance plant disease detection with new datasets and efficient distillation
Researchers have developed new methods for plant leaf disease classification to aid in early detection and treatment. One approach involves training a new base model using the DenseNet201 architecture on a custom datase…
-
Object detection models show mixed robustness to quantization and input degradations
A new study investigates how post-training quantization (PTQ) affects the robustness of YOLO object detection models when faced with real-world input degradations like noise and blur. Researchers evaluated various preci…