DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
☆665Nov 16, 2026Updated this week
Alternatives and similar repositories for DFloat11
Users that are interested in DFloat11 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Aug 26, 2025Updated last year
- Code repository for ICLR 2025 paper "LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid"☆28Mar 2, 2025Updated last year
- Fused BF16 Huffman GEMV Inference kernel☆22Apr 22, 2026Updated 6 months ago
- [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆3,969Sep 6, 2026Updated 2 months ago
- ☆13Jun 27, 2025Updated 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.
- Model Compression Toolbox for Large Language Models and Diffusion Models☆804Aug 14, 2025Updated last year
- ☆96May 25, 2025Updated last year
- Fork of the official DF11 ComfyUI custom node that aims to support other model architectures, and add support for LoRAs (selected models …☆56Oct 22, 2026Updated 3 weeks ago
- A ComfyUI extention for BAGEL dfloat11 Quantized wrapper (Unified Model for Multimodal Understanding and Generation)☆25May 30, 2025Updated last year
- Sparse Inferencing for transformer based LLMs☆223Mar 25, 2026Updated 7 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆4,014Jan 17, 2026Updated 10 months ago
- [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation☆609Nov 11, 2025Updated last year
- ComfyUI nodes collection: better TAESD previews (including batch previews), improved HyperTile and Deep Shrink nodes☆155Sep 16, 2026Updated 2 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆397Apr 13, 2025Updated last year
- 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.
- The official code that integrates MagCache (Fast Video Generation with Magnitude-Aware Cache) with ComfyUI.☆275Nov 27, 2025Updated 11 months ago
- ☆96Jun 20, 2025Updated last year
- ☆54May 20, 2025Updated last year
- ☆34May 7, 2025Updated last year
- flux distillation and stuff☆121Jun 22, 2025Updated last year
- Official implementation of Half-Quadratic Quantization (HQQ)☆964Feb 26, 2026Updated 8 months ago
- ComfyUI implemtation for NAG☆321Nov 3, 2025Updated last year
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆1,269Feb 25, 2026Updated 8 months ago
- RAM is all you need☆287Sep 20, 2026Updated last month
- 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.
- PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度☆1,707Updated this week
- SD.Next Quantization Engine☆139Updated this week
- Work in progress.☆82Nov 25, 2025Updated 11 months ago
- Official implementation of "Normalized Attention Guidance"☆207Nov 3, 2026Updated 2 weeks ago
- Official implementation of MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement (ICLR2026)☆301Mar 24, 2026Updated 7 months ago
- Pusa: Thousands Timesteps Video Diffusion Model☆685Feb 13, 2026Updated 9 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆441Nov 20, 2025Updated 11 months ago
- ☆130Mar 18, 2026Updated 8 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆1,390Jun 8, 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.
- ComfyUI custom node for lightx2v☆95Nov 4, 2026Updated 2 weeks ago
- UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios☆153Apr 9, 2026Updated 7 months ago
- The Python Implementation of CRISP: Clustering Multi-Vector Representations for Denoising and Pruning☆27Jul 27, 2025Updated last year
- ☆13Apr 30, 2025Updated last year
- Fast kernel library for Diffusion inference with multiple compute backends.☆262Updated this week
- Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios,try it in comfyUI☆29Oct 24, 2026Updated 3 weeks ago
- ☆200Jun 22, 2025Updated last year
Are these results useful?