tensorrt
PulseAugur coverage of tensorrt — every cluster mentioning tensorrt across labs, papers, and developer communities, ranked by signal.
- uses SeedVR2 90%
- used by DagsHub 70%
- competes with ONNX Runtime 70%
- affiliated with SeedVR2 70%
- used by ScienceCast 70%
- used by CatalyzeX 70%
- used by Gotit.pub 70%
- used by NVIDIA Jetson Orin Nano 8GB 70%
- used by NVIDIA Jetson AGX Orin 64GB 70%
- used by alphaXiv 70%
- affiliated with ONNX Runtime 50%
- affiliated with NVIDIA Jetson Orin Nano 8GB 50%
9 day(s) with sentiment data
-
Lightweight HMMF-Net achieves high accuracy in fish feeding assessment
Researchers have developed HMMF-Net, a novel lightweight network designed for accurate fish feeding intensity assessment in aquaculture. This multimodal architecture effectively combines visual and acoustic data, overco…
-
InstantHMR enables real-time 3D human mesh recovery on mobile devices
Researchers have developed InstantHMR, a new open-source framework for real-time 3D human mesh recovery on mobile devices. This system is designed for speed and accuracy, achieving significantly faster inference times t…
-
New PanoDent-KD pipeline enables specialized dental radiograph detection on embedded systems
Researchers have developed PanoDent-KD, a new pipeline for detecting dental abnormalities in panoramic radiographs. This system utilizes knowledge distillation from a generalist model to create specialized detectors for…
-
New framework ProCerDCL verifies deep learning compiler optimizations
Researchers have developed ProCerDCL, a new framework designed for efficient black-box probabilistic verification of deep learning compiler optimizations. This tool assesses the probability of a property violation again…
-
AI inference optimized with multi-megakernel approach, outperforming single kernels
Researchers have developed a new framework for optimizing streaming inference in AI models by strategically composing multiple megakernels rather than relying on a single monolithic one. This approach, tested across NH-…
-
NVIDIA powers European retailers with open AI models for cost savings and efficiency
NVIDIA is enabling European retailers to leverage open AI models and physical intelligence for various applications. Companies like Shopify are fine-tuning open models to achieve high accuracy and significantly reduce i…
-
llama.cpp releases pre-versions; depth estimation benchmarked for Jetson AGX Orin
The llama.cpp project has released several pre-release versions, including b11848, b11852, and b11799, which introduce various updates and bug fixes. Notably, release b11848 includes support for concurrent downloads acr…
-
SparkLLM releases Spark-X2.6-4B for on-device agents and coding
SparkLLM has released Spark-X2.6-4B, a new compact language model designed for on-device agents and real-world applications. This model builds upon its predecessor, Spark-X2.5-4B, with enhanced post-training capabilitie…
-
AI model pruning enhances speed-sign recognition for automotive systems
Researchers have developed a novel method for optimizing speed-limit sign recognition in automotive systems by employing channel replay pruning on YOLO-family networks. This technique significantly reduces the number of…
-
Edge GPU AI performance bottlenecked by memory bandwidth, not FLOPs
A new research paper highlights that the performance of query-based segmentation decoders on edge GPUs is primarily limited by memory bandwidth rather than computational power (FLOPs). The study, which profiles models l…
-
ComfyUI Video Upscaler Adds W4A8 Quantization Support
A new version of the ComfyUI-SeedVR2-VideoUpscaler-with-TensorRT tool, v1.6.6, has been released, introducing support for W4A8 quantization. This update aims to improve image quality over NVFP4 while maintaining similar…
-
Nvidia GPU Terms Explained for AI Engineers
This article defines essential GPU terms for AI engineers, covering concepts from CUDA cores to NVLink. It explains how these NVIDIA GPU concepts influence model fitting, execution speed, and scalability. The piece aims…
-
ComfyUI Video Upscaler Updated for Low-VRAM Systems
A new version of the ComfyUI-SeedVR2-VideoUpscaler-with-TensorRT tool has been released, specifically targeting users with 6GB or 8GB of VRAM. Version 1.6.0 introduces a DisTorch2 DiT Loader Node and Phase 2 VRAM Contro…
-
ComfyUI Tool Update Stabilizes VRAM for Lower-End GPUs
A new version of the ComfyUI-SeedVR2-VideoUpscaler-with-TensorRT tool has been released, specifically addressing VRAM usage spikes during Diffusion Transformer (DiT) processing. This update, version 1.5.7, aims to stabi…
-
Ultralytics YOLO Evolution: From YOLOv5 to YOLO27 Detailed in New Paper
A comprehensive paper reviews the evolution of Ultralytics' YOLO object detection models, detailing advancements from YOLOv5 through the latest YOLO27. YOLO27 introduces a dual-architecture strategy, with compact versio…
-
VPEngine framework boosts robotic vision inference speed by 3x
Researchers have developed VPEngine, a novel framework designed to optimize GPU usage for robotic vision tasks. This system utilizes a shared foundation model to extract image representations, which are then efficiently…
-
TokenMask simplifies vision transformer segmentation, boosting efficiency
Researchers have developed TokenMask, a novel method for vision transformer segmentation that operates directly in the token space, eliminating the need for dense spatial feature map reconstruction. This approach simpli…
-
AI framework enables real-time fruit detection on edge hardware
Researchers have developed a framework for real-time fruit detection and video analytics on embedded hardware, specifically the NVIDIA Jetson Orin Nano Super. The system utilizes a lightweight YOLO26s detector trained o…
-
New 'woma' foundation model sets real-time endoscopy standard
Researchers have developed "woma," a real-time foundation model for gastrointestinal endoscopy, trained without labels on approximately one million endoscopy frames. This model can be fine-tuned for specific tasks, such…
-
Running multiple AI models on one GPU: challenges and considerations
This article explores the challenges of running multiple AI models on a single GPU, focusing on potential conflicts and performance degradation. It highlights key questions to consider regarding model interference, syst…