Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.
☆253Jun 29, 2026Updated 3 weeks ago
Alternatives and similar repositories for sparser-faster-llms
Users that are interested in sparser-faster-llms are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official Codebase: LT2: Linear-Time Looped Transformers.☆49May 27, 2026Updated last month
- DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation☆240Feb 18, 2026Updated 5 months ago
- ☆34Feb 1, 2026Updated 5 months ago
- ☆25May 14, 2026Updated 2 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆86May 29, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention☆246May 25, 2026Updated last month
- ☆22Jul 10, 2026Updated last week
- Official code for "How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs"☆24Feb 10, 2026Updated 5 months ago
- Code with CliqueFlowmer model for Optimal Computational Materials Discovery☆17Apr 21, 2026Updated 3 months ago
- Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization☆22Feb 18, 2026Updated 5 months ago
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆274May 6, 2026Updated 2 months ago
- ☆22May 5, 2025Updated last year
- ☆15May 20, 2026Updated 2 months ago
- Population Based Training of Petri Dish Neural Cellular Automata☆16Apr 14, 2026Updated 3 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A lightweight inference engine supporting speculative speculative decoding (SSD).☆970May 10, 2026Updated 2 months ago
- Quartet II Official Code☆76May 1, 2026Updated 2 months ago
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆625Feb 15, 2026Updated 5 months ago
- MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models☆27May 23, 2026Updated last month
- Fast Polar Decomposition for Muon☆166Jul 2, 2026Updated 2 weeks ago
- ☆16Jun 15, 2026Updated last month
- The implementation for ThreadWeaver Adaptive Threading for Efficient Parallel Reasoning in Language Models☆67Apr 8, 2026Updated 3 months ago
- ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis☆15Aug 4, 2025Updated 11 months ago
- 📄Small Batch Size Training for Language Models☆82Mar 18, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆606May 24, 2026Updated last month
- ☆796Apr 16, 2026Updated 3 months ago
- Generative Modeling with Bayesian Sample Inference☆24May 17, 2025Updated last year
- Efficient non-uniform quantization with GPTQ for GGUF☆64Sep 17, 2025Updated 10 months ago
- We propose Bidirectional Evolutionary Search (BES), a search framework that couples forward candidate evolution with backward goal decomp…☆166May 28, 2026Updated last month
- AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)☆46May 20, 2026Updated 2 months ago
- The training codes of Jasper-Token-Compression-600M☆20Nov 19, 2025Updated 8 months ago
- Delta Attention Residuals - supplementary code and pretrained models☆40May 20, 2026Updated 2 months ago
- This repositories contains the reference implementation for the Sparse Delta Memory paper.More precisely, it contains the model definitio…☆30Jul 9, 2026Updated last week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆363Jun 23, 2025Updated last year
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆139Sep 24, 2025Updated 9 months ago
- ☆35Jul 8, 2026Updated last week
- ☆135May 29, 2025Updated last year
- 🖥 Neural Computers' Data Engine☆201May 19, 2026Updated 2 months ago
- ☆45Feb 28, 2026Updated 4 months ago
- Code for the Avey-B paper (https://arxiv.org/abs/2602.15814)☆32Feb 21, 2026Updated 4 months ago