PyTorch emulation library for Microscaling (MX)-compatible data formats
☆353Jun 18, 2025Updated 10 months ago
Alternatives and similar repositories for microxcaling
Users that are interested in microxcaling are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Implementation of Microscaling data formats in SystemVerilog.☆32Jul 6, 2025Updated 9 months ago
- ☆172Mar 9, 2023Updated 3 years ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆505Nov 26, 2024Updated last year
- Official implementation for Training LLMs with MXFP4☆124Apr 25, 2025Updated last year
- The official implementation of the EMNLP 2023 paper LLM-FP4☆224Dec 15, 2023Updated 2 years 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.
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆762Aug 6, 2025Updated 8 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆280Jul 16, 2025Updated 9 months ago
- LLM Inference with Microscaling Format☆34Nov 12, 2024Updated last year
- Pytorch implementation of our paper accepted by NeurIPS 2022 -- Learning Best Combination for Efficient N:M Sparsity☆22Jan 13, 2023Updated 3 years ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆310Mar 10, 2026Updated last month
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆179Nov 11, 2025Updated 5 months ago
- ☆49May 20, 2025Updated 11 months ago
- Unit Scaling demo and experimentation code☆16Mar 12, 2024Updated 2 years ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆834Mar 6, 2025Updated last year
- 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.
- Microsoft Automatic Mixed Precision Library☆636Dec 1, 2025Updated 4 months ago
- ☆590Oct 29, 2024Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆125Jul 4, 2025Updated 9 months ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,291Updated this week
- This repository contains the experimental PyTorch native float8 training UX☆226Aug 1, 2024Updated last year
- A framework to compare low-bit integer and float-point formats☆77Feb 6, 2026Updated 2 months ago
- ☆107Feb 26, 2026Updated 2 months ago
- Fast low-bit matmul kernels in Triton☆445Updated this week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆337Jul 2, 2024Updated 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.
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆390Feb 14, 2025Updated last year
- ☆66Apr 26, 2025Updated last year
- AFPQ code implementation☆23Nov 6, 2023Updated 2 years ago
- Debug print operator for cudagraph debugging☆15Aug 2, 2024Updated last year
- [ACL 2025 Main] EfficientQAT: Efficient Quantization-Aware Training for Large Language Models☆337Apr 10, 2026Updated 3 weeks ago
- ☆35Dec 22, 2025Updated 4 months ago
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆9,638Updated this week
- PyTorch native quantization and sparsity for training and inference☆2,796Updated this week
- ☆20Feb 12, 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.
- [ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.☆891Nov 26, 2025Updated 5 months ago
- Work in progress.☆80Nov 25, 2025Updated 5 months ago
- ☆63Jul 21, 2024Updated last year
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆391Apr 13, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,061Sep 4, 2024Updated last year
- An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization☆171Nov 26, 2025Updated 5 months ago
- FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/☆1,557Updated this week