IST-DASLab / SparseFinetuningLinks
Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
☆42Updated last year
Alternatives and similar repositories for SparseFinetuning
Users that are interested in SparseFinetuning are comparing it to the libraries listed below
Sorting:
- Repository for CPU Kernel Generation for LLM Inference☆26Updated 2 years ago
- QuIP quantization☆57Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆61Updated 10 months ago
- DPO, but faster 🚀☆44Updated 8 months ago
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆42Updated last year
- ☆51Updated 9 months ago
- Work in progress.☆72Updated last month
- The evaluation framework for training-free sparse attention in LLMs☆90Updated 2 months ago
- CUDA and Triton implementations of Flash Attention with SoftmaxN.☆73Updated last year
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- PB-LLM: Partially Binarized Large Language Models☆153Updated last year
- ☆55Updated last year
- ☆127Updated last year
- This repository contains code for the MicroAdam paper.☆19Updated 8 months ago
- ☆20Updated 4 months ago
- ☆139Updated 6 months ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated last month
- Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"☆98Updated 10 months ago
- ☆14Updated last month
- ☆51Updated 2 months ago
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆17Updated 10 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆76Updated last year
- From GaLore to WeLore: How Low-Rank Weights Non-uniformly Emerge from Low-Rank Gradients. Ajay Jaiswal, Lu Yin, Zhenyu Zhang, Shiwei Liu,…☆47Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- Official implementation for Training LLMs with MXFP4☆75Updated 4 months ago
- Using FlexAttention to compute attention with different masking patterns☆44Updated 11 months ago
- Vocabulary Parallelism☆20Updated 5 months ago
- Official PyTorch implementation of "GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance" (ICML 2025)☆42Updated last month
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 8 months ago