Trending

[D] Anyone else using Tensordock cloud GPU and now feeling frustrated?

The AI team at Google have reached the surprising conclusion that quantizing weights from 16-bits to 4-bits leads to a 4x reduction of VRAM usage!

TensorFlow implementation for optimizers

[D] Google just released a new generation of TPUs. Who actually uses TPUs in production?

[P] Simple standalone TFRecords dataset reader with Random Access and search-in capabilities

How we used NVIDIA TensorRT-LLM with Blackwell B200 to achieve 303 output tokens per second on DeepSeek R1

[D] Comparing GenAI Inference Engines: TensorRT-LLM, vLLM, Hugging Face TGI, and LMDeploy

Tensorflow not detecting RTX 5080 GPU - Help [D]

huggingface

Save item

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

ultralytics

Save item

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite