ByteDance-Seed / SDP4BitLinks
official implementation of paper SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
☆44Updated last year
Alternatives and similar repositories for SDP4Bit
Users that are interested in SDP4Bit are comparing it to the libraries listed below
Sorting:
- SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models☆38Updated 11 months ago
- Support mixed-precsion inference with vllm☆84Updated 6 months ago
- Single-thread, end-to-end C++ implementation of the Bitnet (1.58-bit weight) model☆14Updated last year
- An implementation of Explicit Shortcut model for One-step Diffusion Generation☆67Updated this week
- Mixed precision inference by Tensorrt-LLM☆80Updated last year
- ☆24Updated 9 months ago
- KFunca: A minimalist, high-performance GPU-based automatic differentiation framework☆29Updated 5 months ago
- ☆21Updated last year
- University of Toronto / ECE1782 Programming Massively Parallel Multiprocessors and Heterogeneous Systems / Project: an optimized CUDA Imp…☆25Updated last year
- computing the non-convex risk parity porfolio problems by the non-convex quadratic approxiamtion (NCQA), interior point method (IPM) and…☆26Updated 3 years ago
- An easy-to-use vector database.☆37Updated 10 months ago
- Implementation of semantic segmentation of FCN structure using KITTI road dataset😝😝😝☆34Updated last year
- Typeless Programming Language `sicpy` and Compiler;☆32Updated 2 years ago
- ☆12Updated 2 years ago
- StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving☆21Updated last year
- [COLING Demos 2025] an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs☆38Updated 11 months ago
- By converting single-channel grayscale images into multi-channel images through various data enhancement techniques, SimOTM enhances the …☆30Updated 8 months ago
- This includes the original implementation of Retrieval-Oriented Knowledge for Click-Through Rate Prediction.☆21Updated last year
- ☆75Updated last year
- Official Implementation of "Pay Attention to What You Need"☆44Updated 11 months ago
- Build CUDA Neural Network From Scratch☆22Updated last year
- variable length int encoding☆16Updated last week
- PawMark is a platform for developers to build, schedule and monitor data pipelines.☆22Updated last year
- ☆41Updated 8 months ago
- QRec is an algorithm that helps you quickly find the largest fixed-aspect, axis-aligned rectangle that can be inscribed in any given poly…☆27Updated 7 months ago
- ☆19Updated 9 months ago
- ☆29Updated 2 years ago
- [NeurIPS 25 @ ER] Long-Context Modeling with Dynamic Hierarchical Sparse Attention for On-Device LLMs☆73Updated 2 months ago
- ☆62Updated last year
- ROSE: Robust Cross Supervision with Neighborhood Mining for Source-free Graph Domain Adaptation☆19Updated last year