A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Repository Index
132,241 visible repositories in the index
1–6 of 6 · Most stars
NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.
Adapting Meta AI's Segment Anything to Downstream Tasks with Adapters and Prompts
- 2d-segmentation
- adapter
- camouflage-images
- camouflaged-object-detection
A Semantic Controllable Self-Supervised Learning Framework to learn general human representations from massive unlabeled human images, which can benefit downstream human-centric tasks to the maximum extent
- cvpr2023
- self-supervised-learning
- human-centric
[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
- iemocap
- pytorch-implementation
- speech-emotion-recognition
- speech-representation
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper
- imagenet21k
- pretraining
- downstream
- semantic-softmax