☆53May 20, 2025Updated last year
Alternatives and similar repositories for fp4-all-the-way
Users that are interested in fp4-all-the-way are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆129Mar 18, 2026Updated 7 months ago
- Quartet II Official Code☆83May 1, 2026Updated 5 months ago
- Official implementation for Training LLMs with MXFP4☆130Apr 25, 2025Updated last year
- ☆126Feb 26, 2026Updated 7 months ago
- ☆18Sep 22, 2024Updated 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.
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆204Sep 2, 2026Updated last month
- Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training☆41May 4, 2026Updated 5 months ago
- Work in progress.☆82Nov 25, 2025Updated 10 months ago
- ☆25Oct 31, 2024Updated last year
- Code for MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization☆30Oct 6, 2026Updated last week
- ☆36Mar 12, 2025Updated last year
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆204Apr 21, 2026Updated 5 months ago
- LLM Inference with Microscaling Format☆35Nov 12, 2024Updated last year
- 🔀 yet another mixture of experts☆23Jun 5, 2026Updated 4 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.
- ☆14May 4, 2026Updated 5 months ago
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆365Jul 17, 2026Updated 3 months ago
- HALO: Hadamard-Assisted Low-Precision Optimization and Training method for finetuning LLMs. 🚀 The official implementation of https://arx…☆32Feb 17, 2025Updated last year
- Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention☆80Apr 7, 2026Updated 6 months ago
- NVFP4 Flash-Attention 4 on BlackWell☆68Sep 26, 2026Updated 3 weeks ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆354Mar 10, 2026Updated 7 months ago
- ☆40Dec 14, 2025Updated 10 months ago
- Quantized LLM training in pure CUDA/C++.☆262Aug 31, 2026Updated last month
- Minimal and highly hackable implementation of Looped Transformers with GPT☆25Mar 8, 2026Updated 7 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.
- ☆32Jul 2, 2025Updated last year
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆30Jul 24, 2025Updated last year
- [ACL 2026 🔥] CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark☆38Aug 17, 2026Updated 2 months ago
- ☆64Jul 10, 2025Updated last year
- The official implementation of NOSA (EMNLP 2026 main)☆19Sep 28, 2026Updated 2 weeks ago
- ☆54May 19, 2025Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆263Jun 15, 2025Updated last year
- Fast low-bit matmul kernels in Triton☆488Oct 1, 2026Updated 2 weeks ago
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆268Aug 9, 2025Updated last year
- Code for "Fast Sparse ConvNets" CVPR2020 submissions☆12Nov 20, 2019Updated 6 years ago
- ☆16Dec 9, 2023Updated 2 years ago
- The open-source code of MetaStone-S1.☆106Aug 1, 2025Updated last year
- Code repo for the paper "SpinQuant LLM quantization with learned rotations"☆438Feb 14, 2025Updated last year
- [ICML 2025] MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design☆32Jul 4, 2025Updated last year
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆258Updated this week