Quantization-Aware Training for NVFP4 Reasoning Models
☆14Jul 10, 2026Updated 4 months ago
Alternatives and similar repositories for ReQAT
Users that are interested in ReQAT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Oct 29, 2026Updated 2 weeks ago
- [NeurIPS 2023] Token-Scaled Logit Distillation for Ternary Weight Generative Language Models☆18Dec 6, 2023Updated 2 years ago
- RobuQ: Pushing DiTS to W1.58A2 via Robust Activation Quantization☆17Oct 14, 2026Updated 3 weeks ago
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆14Oct 30, 2026Updated last week
- [ICML 2026 Spotlight] Official implementation of TetraJet-v2: Accurate NVFP4 Training for LLMs, with fully-NVFP4 linear layer with unbias…☆19Jul 3, 2026Updated 4 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.
- ☆18Jul 19, 2026Updated 3 months ago
- ☆10Nov 4, 2022Updated 4 years ago
- CuteDSL Swizzle Visualize Tool☆14Feb 22, 2026Updated 8 months ago
- TernGEMM: General Matrix Multiply Library with Ternary Weights for Fast DNN Inference☆14Feb 22, 2022Updated 4 years ago
- [ICML 2026] Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution☆25Oct 14, 2026Updated 3 weeks ago
- LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)☆22Dec 22, 2025Updated 10 months ago
- ☆15Oct 9, 2023Updated 3 years ago
- ☆11Aug 26, 2024Updated 2 years ago
- Reasoning tree with validation☆19Jul 28, 2026Updated 3 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.
- Make FP4 on 5090 Great Again☆24Jul 20, 2026Updated 3 months ago
- Code and reproducibility artifacts for reconstructing megakernel persistence with CUDA PDL☆27Aug 5, 2026Updated 3 months ago
- 数据链路层协议在线模拟器☆10May 18, 2026Updated 5 months ago
- Code repository for the SOSP'25 paper DCP: Addressing Input Dynamism In Long-Context Training via Dynamic Context Parallelism.☆23Nov 28, 2025Updated 11 months ago
- Layer-wise Pruning of Transformer Heads for Efficient Language Modeling☆22Feb 22, 2022Updated 4 years ago
- PyTorch CoreSIG☆58Dec 30, 2024Updated last year
- [ICML 2024]: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models☆11May 19, 2024Updated 2 years ago
- Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention☆84Apr 7, 2026Updated 7 months ago
- Pytorch implementation of "Oscillation-Reduced MXFP4 Training for Vision Transformers" on DeiT Model Pre-training☆41May 4, 2026Updated 6 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference.☆25May 20, 2026Updated 5 months ago
- Singularity is a desktop Matrix client written in rust using tauri.☆16Oct 21, 2026Updated 3 weeks ago
- ☆22Sep 5, 2024Updated 2 years ago
- [COLM 2025] Official PyTorch implementation of "Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models"☆78Jul 8, 2025Updated last year
- ☆11Oct 9, 2023Updated 3 years ago
- [IEEE NER 2023] EffiE: Efficient Convolutional Neural Network for Real-Time EMG Pattern Recognition System on Edge Devices☆22Sep 28, 2023Updated 3 years ago
- ☆19May 29, 2026Updated 5 months ago
- Sample Codes using NVSHMEM on Multi-GPU☆30Jan 22, 2023Updated 3 years ago
- Official implementation of LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents☆34Oct 23, 2026Updated 2 weeks ago
- 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.
- ☆38Jul 27, 2026Updated 3 months ago
- The official code implement of <Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima>☆19Jun 17, 2026Updated 4 months ago
- 简易 OI 交题服务器☆10Dec 12, 2025Updated 11 months ago
- ☆37Aug 7, 2025Updated last year
- ☆13Sep 29, 2026Updated last month
- Repo for "STAR: Spectral Truncation and Rescale for Model Merging" [NAACL 2025]☆11Oct 22, 2026Updated 3 weeks ago
- ☆23Dec 18, 2023Updated 2 years ago
Are these results useful?