DS3Lab / CocktailSGDLinks
☆27Updated 2 years ago
Alternatives and similar repositories for CocktailSGD
Users that are interested in CocktailSGD are comparing it to the libraries listed below
Sorting:
- ☆19Updated 2 years ago
- Experiment of using Tangent to autodiff triton☆81Updated last year
- ☆14Updated 2 months ago
- This repository contains code for the MicroAdam paper.☆19Updated 9 months ago
- Muon fsdp 2☆43Updated last month
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.☆70Updated last year
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆68Updated 9 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- ☆83Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- Fast and memory-efficient exact attention☆69Updated 6 months ago
- ☆29Updated 10 months ago
- ☆20Updated 2 years ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 11 months ago
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆94Updated last year
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆87Updated 2 months ago
- ☆111Updated last year
- ☆53Updated last year
- Repository for CPU Kernel Generation for LLM Inference☆26Updated 2 years ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- The evaluation framework for training-free sparse attention in LLMs☆93Updated 3 months ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated 11 months ago
- ☆46Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 9 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆239Updated 3 weeks ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- Simple and efficient pytorch-native transformer training and inference (batched)☆78Updated last year
- ☆142Updated 7 months ago
- ☆94Updated 3 years ago
- Code for studying the super weight in LLM☆117Updated 9 months ago