ensemble-core / NdLinearLinks
NdLinear by Ensemble is a drop-in PyTorch module that shrinks your models with no accuracy loss. It powers the Ensemble Platform—upload any model and get back a smaller, faster version, ready to deploy. Export to all frameworks (ONNX, TensorRT, SNPE, and more). Try it now → https://app.ensemblecore.ai/signup
☆301Updated 3 months ago
Alternatives and similar repositories for NdLinear
Users that are interested in NdLinear are comparing it to the libraries listed below
Sorting:
- ⏰ AI conference deadline countdowns☆282Updated this week
- List of startups doing AI & ML☆281Updated 9 months ago
- Repository for ACM India Summer School on Generative AI for Text☆13Updated last year
- ☆44Updated 3 months ago
- PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning☆502Updated 2 weeks ago
- ☆508Updated last week
- GPUGrants - a list of GPU grants that I can think of☆36Updated last week
- List of AI Internships☆126Updated last year
- A repository consisting of paper/architecture replications of classic/SOTA AI/ML papers in pytorch☆365Updated last week
- H-Net: Hierarchical Network with Dynamic Chunking☆727Updated last month
- Official implementation of the paper: "ZClip: Adaptive Spike Mitigation for LLM Pre-Training".☆133Updated 2 weeks ago
- ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"☆112Updated 2 months ago
- Notebook and Scripts that showcase running quantized diffusion models on consumer GPUs☆38Updated 10 months ago
- Reproduction of DeepSeek-R1☆238Updated 5 months ago
- First-principle implementations of groundbreaking AI algorithms using a wide range of deep learning frameworks, accompanied by supporting…☆178Updated 2 months ago
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation☆443Updated last month
- One-stop solutions for Mixture of Experts and Mixture of Depth modules in PyTorch.☆24Updated 3 months ago
- Resources needed to start deep learning research. ML/DL/CV/NLP/ML-SYS/RL/Graphs/Maths/Med image lecture videos from professors at esteeme…☆87Updated last month
- ☆32Updated 2 months ago
- Simple, minimal implementation of the Mamba SSM in one pytorch file. Using logcumsumexp (Heisen sequence).☆122Updated 11 months ago
- ☆89Updated 5 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆146Updated 4 months ago
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models. TMLR 2025.☆105Updated last week
- GPU Kernels☆194Updated 4 months ago
- Attempt to make multiple residual streams from Bytedance's Hyper-Connections paper accessible to the public☆90Updated 3 months ago
- ☆105Updated 2 weeks ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆186Updated last year
- Conference schedule, top papers, and analysis of the data for NeurIPS 2023!☆120Updated last year
- Quick implementation of nGPT, learning entirely on the hypersphere, from NvidiaAI☆290Updated 3 months ago
- ☆196Updated 9 months ago