Hacker News
- Fast Llama 2 on CPUs with Sparse Fine-Tuning and DeepSparse https://neuralmagic.com/blog/fast-llama-2-on-cpus-with-sparse-fine-tuning-and-deepsparse/ 26 comments
- Image Segmentation: Your Ultimate Guide to Easy Deployment and Fast Inferencing https://neuralmagic.com/blog/image-segmentationyour-ultimate-guide-to-easy-deployment-and-fast-inferencing/ 2 comments
- Neural Network inference on commodity CPUs using sparsity https://neuralmagic.com/deepsparse-engine/ 3 comments
- YOLOv5 on CPUs: Sparsifying to Achieve GPU-Level Performance https://neuralmagic.com/blog/benchmark-yolov5-on-cpus-with-deepsparse/ 53 comments
Lobsters
- SparseGPT: Remove 100B Parameters For Free https://neuralmagic.com/blog/sparsegpt-remove-100-billion-parameters-for-free/ 6 comments ai
- DeepSparse: 1,000X CPU Performance Boost & 92% Power Reduction with Sparsified Models in MLPerf™ Inference v3.0 https://neuralmagic.com/blog/neural-magic-scales-up-mlperf-inference-performance-with-demonstrated-power-efficiency-no-gpus-needed/ 8 comments computervision
- [D] DeepSparse: 1,000X CPU Performance Boost & 92% Power Reduction with Sparsified Models in MLPerf™ Inference v3.0 https://neuralmagic.com/blog/neural-magic-scales-up-mlperf-inference-performance-with-demonstrated-power-efficiency-no-gpus-needed/ 3 comments deeplearning
- [P] Sparse Transformers for Inference in a Real-Time Twitter Stream https://neuralmagic.com/blog/classifying-finance-tweets-in-real-time-with-sparse-transformers/ 3 comments machinelearning