Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”
☆199Apr 21, 2026Updated 3 months ago
Alternatives and similar repositories for fouroversix
Users that are interested in fouroversix are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆116Feb 26, 2026Updated 5 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆193Jul 20, 2026Updated last week
- ☆251Nov 19, 2025Updated 8 months ago
- ☆127Mar 18, 2026Updated 4 months ago
- Quartet II Official Code☆77May 1, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2026]A framework to compare low-bit integer and float-point formats☆81May 6, 2026Updated 2 months ago
- [ASPLOS'26] Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter☆174Feb 27, 2026Updated 5 months ago
- UniQL official repository (ICLR 2026)☆17Jan 27, 2026Updated 6 months ago
- MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models☆28Apr 2, 2026Updated 3 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆342Mar 10, 2026Updated 4 months ago
- Fast, memory-efficient attention column reduction (e.g., sum, mean, max)☆49Feb 10, 2026Updated 5 months ago
- Model Compression Toolbox for Large Language Models and Diffusion Models☆796Aug 14, 2025Updated 11 months ago
- NVFP4 Flash-Attention 4 on BlackWell☆31Updated this week
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆116Dec 2, 2025Updated 7 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.
- Code for data-aware compression of DeepSeek models☆75Dec 11, 2025Updated 7 months ago
- [ICML 2025] Official PyTorch implementation of "FlatQuant: Flatness Matters for LLM Quantization"☆223Nov 25, 2025Updated 8 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆852Mar 6, 2025Updated last year
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆418Feb 14, 2025Updated last year
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆324Feb 24, 2026Updated 5 months ago
- [ACL 2026 Main] Code for the paper "ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs"☆28Jun 1, 2026Updated last month
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆524Nov 26, 2024Updated last year
- [CVPR 2026 Highlight] ForeAct: Steering Your VLA with Efficient Visual Foresight Planning☆84May 1, 2026Updated 2 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆732Jul 4, 2026Updated 3 weeks 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.
- ☆16May 27, 2026Updated 2 months ago
- A Quirky Assortment of CuTe Kernels☆1,076Updated this week
- Fast low-bit matmul kernels in Triton☆477Jul 15, 2026Updated 2 weeks ago
- LLM Inference with Microscaling Format☆35Nov 12, 2024Updated last year
- ☆51May 20, 2025Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆280Jul 6, 2025Updated last year
- A WebUI for Side-by-Side Comparison of Media (Images/Videos) Across Multiple Folders☆26Feb 21, 2025Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆158Aug 21, 2025Updated 11 months ago
- [ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆104May 8, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆358Jul 17, 2026Updated last week
- ☆779Jun 2, 2026Updated last month
- Official implementation for Training LLMs with MXFP4☆130Apr 25, 2025Updated last year
- A sparse attention kernel supporting mix sparse patterns☆539Jan 18, 2026Updated 6 months ago
- [ICML 2026] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs☆29Apr 27, 2026Updated 3 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- FA4-based Relative Attention Kernel developed by TML and Colfax☆17Jul 17, 2026Updated last week