Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.
☆263Jun 29, 2026Updated 4 months 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:
- DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation☆325Feb 18, 2026Updated 9 months ago
- ☆34Feb 1, 2026Updated 9 months ago
- Official Codebase: LT2: Linear-Time Looped Transformers.☆70Jul 27, 2026Updated 3 months ago
- Triton kernels and PyTorch ops for Block Attention Residuals (AttnRes)☆90May 29, 2026Updated 5 months ago
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆721Feb 15, 2026Updated 9 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A parallel native tool caling deep search agentic framework with base window retention observation masking context management.☆25Sep 22, 2026Updated last month
- ☆34May 14, 2026Updated 6 months ago
- Official code for "How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs"☆25Feb 10, 2026Updated 9 months ago
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆279May 6, 2026Updated 6 months ago
- ☆23Jul 10, 2026Updated 4 months ago
- Code with CliqueFlowmer model for Optimal Computational Materials Discovery☆17Nov 2, 2026Updated 2 weeks ago
- Official PyTorch Implementation of Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention☆366Oct 11, 2026Updated last month
- ☆10May 16, 2026Updated 6 months ago
- Population Based Training of Petri Dish Neural Cellular Automata☆19Apr 14, 2026Updated 7 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆16Nov 12, 2026Updated last week
- Reproduction code for Lattice Deduction Transformers☆43Oct 29, 2026Updated 3 weeks ago
- A lightweight inference engine supporting speculative speculative decoding (SSD).☆1,021May 10, 2026Updated 6 months ago
- ☆47Feb 28, 2026Updated 8 months ago
- ConfAgents: A Conformal-Guided Multi-Agent Framework for Cost-Efficient Medical Diagnosis☆15Jul 22, 2026Updated 3 months ago
- ☆67Apr 16, 2026Updated 7 months ago
- The implementation for ThreadWeaver Adaptive Threading for Efficient Parallel Reasoning in Language Models☆68Apr 8, 2026Updated 7 months ago
- Efficient Knowledge Injection in LLMs via Self-Distillation (TMLR)☆13Aug 5, 2025Updated last year
- Quartet II Official Code☆86May 1, 2026Updated 6 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆809Sep 11, 2026Updated 2 months ago
- AdaSplash: Adaptive Sparse Flash Attention (aka Flash Entmax Attention)☆55May 20, 2026Updated 5 months ago
- ☆17Jun 15, 2026Updated 5 months ago
- Code for MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models☆35Oct 6, 2026Updated last month
- [EMNLP 2026] MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models☆30Oct 6, 2026Updated last month
- Fast Polar Decomposition for Muon☆190Jul 2, 2026Updated 4 months ago
- 📄Small Batch Size Training for Language Models☆90Mar 18, 2026Updated 8 months ago
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆258Updated this week
- ☆659May 24, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Bidirectional Evolutionary Search (BES), a search framework that couples forward candidate evolution with backward goal decomposition.☆171May 28, 2026Updated 5 months ago
- Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input☆1,337Jun 8, 2025Updated last year
- ☆23May 5, 2025Updated last year
- [NeurIPS 2025] Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale☆14Nov 17, 2025Updated last year
- ☆20Updated this week
- Efficient non-uniform quantization with GPTQ for GGUF☆68Sep 17, 2025Updated last year
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆371Jun 23, 2025Updated last year
Are these results useful?