apd10 / universal_memory_allocationLinks
☆15Updated 3 years ago
Alternatives and similar repositories for universal_memory_allocation
Users that are interested in universal_memory_allocation are comparing it to the libraries listed below
Sorting:
- [ NeurIPS '22 ] Data distillation for recommender systems. Shows equivalent performance with 2-3 orders less data.☆23Updated last year
- ☆14Updated 3 years ago
- A compressed alternative to matrix multiplication using state-of-the art compression ROBE-Z☆9Updated last year
- Differentiable Product Quantization for End-to-End Embedding Compression.☆62Updated 2 years ago
- Time-based Sequence Model for Personalization and Recommendation Systems☆49Updated 3 years ago
- Light-weight GPU kernel interface for graph operations☆15Updated 5 years ago
- [KDD 2022] AutoShard: Automated Embedding Table Sharding for Recommender Systems☆22Updated 2 years ago
- A Learnable LSH Framework for Efficient NN Training☆31Updated 3 years ago
- PyTorch implementation of HashedNets☆36Updated 2 years ago
- Set of datasets for the deep learning recommendation model (DLRM).☆47Updated 2 years ago
- ☆19Updated last year
- [NeurIPS 2022] DreamShard: Generalizable Embedding Table Placement for Recommender Systems☆29Updated 2 years ago
- "Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices", official implementation☆29Updated 4 months ago
- ☆14Updated 3 years ago
- Research and development for optimizing transformers☆126Updated 4 years ago
- MLPruning, PyTorch, NLP, BERT, Structured Pruning☆20Updated 3 years ago
- Accelerating Recommender model training by leveraging popular choices -- VLDB 2022☆30Updated 8 months ago
- Efficient LDA solution on GPUs.☆24Updated 6 years ago
- [ICLR 2022] Code for paper "Exploring Extreme Parameter Compression for Pre-trained Language Models"(https://arxiv.org/abs/2205.10036)☆22Updated 2 years ago
- ☆27Updated 5 years ago
- ☆12Updated 4 years ago
- Confident Adaptive Transformers☆12Updated 4 years ago
- [ NeurIPS '22 ] ∞-AE model's implementation in JAX. Kernel-only method outperforms complicated SoTA models with a closed-form solution an…☆55Updated last year
- Accelerated Confergence for Counterfactual Learning to Rank☆17Updated 3 years ago
- ☆18Updated 3 years ago
- ☆12Updated 3 years ago
- ☆10Updated 4 years ago
- ☆70Updated 3 years ago
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆61Updated 3 years ago
- Code for COMET: Cardinality Constrained Mixture of Experts with Trees and Local Search☆10Updated last year