Quantize transformers to any learned arbitrary 4-bit numeric format
☆61Jul 2, 2026Updated 4 months ago
Alternatives and similar repositories for any4
Users that are interested in any4 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- CATransformers is a framework for joint neural network and hardware architecture search.☆25Mar 17, 2026Updated 7 months ago
- This repository contains the training code of ParetoQ introduced in our work "ParetoQ Scaling Laws in Extremely Low-bit LLM Quantization"☆137Oct 15, 2025Updated last year
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆440Feb 14, 2025Updated last year
- Fast Hadamard transform in CUDA, with a PyTorch interface☆356Mar 10, 2026Updated 7 months ago
- LLM Inference with Microscaling Format☆35Nov 12, 2024Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Compute Where It Counts: Scaling both speed and quality with training compute☆13Sep 18, 2025Updated last year
- Open-source SM120 (Blackwell) SASS assembler — encode, schedule & assemble GPU machine code, including all tensor-core instructions.☆12Updated this week
- [NeurIPS 2025 (spotlight)] HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs☆17Dec 17, 2025Updated 10 months ago
- ☆15Apr 11, 2024Updated 2 years ago
- The official implementation of NOSA (EMNLP 2026 main)☆19Sep 28, 2026Updated last month
- ☆198Jun 22, 2025Updated last year
- [ICLR25] STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs☆19Jun 3, 2025Updated last year
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆540Nov 26, 2024Updated last year
- PyTorch Quantization Framework For OCP MX Datatypes.☆16May 30, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- soundvista☆18Dec 31, 2025Updated 10 months ago
- Create your own local code autocomplete model, fine-tuned on your custom code repository, for use in editors like VS Code or Neovim.☆19Sep 14, 2026Updated last month
- Official implementation of Self-Taught Agentic Long Context Understanding (ACL 2025).☆14Sep 22, 2025Updated last year
- ☆127Feb 26, 2026Updated 8 months ago
- SS2 HRTF Dataset - Reality Labs Research Audio☆19May 22, 2026Updated 5 months ago
- [ICLR 2023] PyTorch code for DFPC: Data flow driven pruning of coupled channels without data.☆15Aug 25, 2023Updated 3 years ago
- CroissAttn: FP4 attention forward and backward, with analysis of stochastic rounding, zero-sum softmax gradients, and sampled centering.☆15Oct 25, 2026Updated last week
- A Production-Ready Causal Learning Library for Industrial Applications☆16Feb 3, 2026Updated 9 months ago
- Pytorch implementation of our paper accepted by ECCV 2022-- Fine-grained Data Distribution Alignment for Post-Training Quantization☆16Sep 13, 2022Updated 4 years 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.
- Enabling sustainable AI with a collection of carbon modeling and optimization frameworks☆17Jun 22, 2026Updated 4 months ago
- [ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitt…☆96Apr 8, 2025Updated last year
- d-Matrix DMX Compressor: A Pytorch toolkit for nn.Module transformations supporting advanced quantization, sparsity, and elementwise func…☆21Sep 24, 2026Updated last month
- GoldFinch and other hybrid transformer components☆47Jul 20, 2024Updated 2 years ago
- Speed-of-Light SW efficiency by using ultra low-latency primitives for comms collectives☆13Apr 8, 2026Updated 6 months ago
- Procedural Knowledge at Scale Improves ReasoningThis repository contains the minimal, end-to-end pipeline for reproducing the paper resul…☆21Apr 1, 2026Updated 7 months ago
- High-performance GPU kernels for Ads and Recsys model training, independently implemented and optimized for real-world workloads and mode…☆57Updated this week
- Qwen3.6/3.8-27B on one RTX 5090: 576K pooled context across 12 sessions at FP8-level quality from 5.75 bpw. EXL3 trellis weights, 4-bit t…☆28Oct 23, 2026Updated last week
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The official implementation of the EMNLP 2023 paper LLM-FP4☆227Dec 15, 2023Updated 2 years ago
- Code for the paper "Goals as Reward Producing Programs"☆14Dec 5, 2024Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆162Aug 21, 2025Updated last year
- Directed masked autoencoders☆15Mar 25, 2026Updated 7 months ago
- Adamas: Hadamard Sparse Attention for Efficient Long-context Inference☆15Oct 1, 2026Updated last month
- Official implementation of AdvGame https//arxiv.org/abs/2512.20806☆22May 6, 2026Updated 5 months ago
- IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse☆146Mar 14, 2026Updated 7 months ago