Easy recipes to speed up latency of Flux, QwenImage, and LTX-2 with NVFP4 and MXFP8 on Blackwell.
☆14Apr 10, 2026Updated 7 months ago
Alternatives and similar repositories for diffusers-blackwell-quants
Users that are interested in diffusers-blackwell-quants are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11May 21, 2026Updated 5 months ago
- [ASPLOS 2026] M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization.☆17Jan 29, 2026Updated 9 months ago
- NVFP4 Flash-Attention 4 on BlackWell☆69Sep 26, 2026Updated last month
- a repo to study TensorRT Plugin☆11Apr 30, 2025Updated last year
- ☆30Apr 5, 2026Updated 7 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.
- ☆15Updated this week
- [CVPR 2025] The official implementation of "CacheQuant: Comprehensively Accelerated Diffusion Models"☆51Nov 2, 2025Updated last year
- Tool to collect debug logs from NVIDIA server components, in band and out-of-band.☆10Oct 15, 2026Updated last month
- ☆37Mar 7, 2025Updated last year
- MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI tr…☆167Updated this week
- Basic floating-point components for RISC-V processors☆12Aug 13, 2017Updated 9 years ago
- My attempt to improve the speed of the newton schulz algorithm, starting from the dion implementation.☆42Apr 30, 2026Updated 6 months ago
- A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.☆24Jul 18, 2025Updated last year
- Claude Code agent skills for writing optimized Triton GPU kernels☆15Mar 6, 2026Updated 8 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆10Mar 11, 2017Updated 9 years ago
- A python library for building adaptors that integrate applications with Open Job Description jobs☆13Nov 4, 2026Updated last week
- Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66…☆56Aug 25, 2026Updated 2 months ago
- ☆27Mar 25, 2025Updated last year
- [ECCV24] MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization☆50Nov 27, 2024Updated last year
- Code for the papers: “Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling” and “Adaptive Block-Scaled Data Types”☆211Apr 21, 2026Updated 6 months ago
- (AAAI-2025 Oral) MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models☆14Jul 8, 2025Updated last year
- Implementation of Microscaling data formats in SystemVerilog.☆35Nov 6, 2026Updated last week
- Qwen-Image's DiT inference with TensorRT-10☆21Oct 13, 2025Updated last year
- 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.
- It is a speech to text project. Upload an audio file and get the transcriptions of the audio. It uses OpenAI's Whisper model☆12Jan 17, 2025Updated last year
- FLA but cuTile☆27Apr 17, 2026Updated 7 months ago
- A demonstrative example of running SGLang Diffusion with DP router☆26Mar 15, 2026Updated 8 months ago
- Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling☆13Sep 3, 2025Updated last year
- MORPH: PDE Foundation Models with Arbitrary Data Modality☆32Sep 24, 2026Updated last month
- ☆17Jul 17, 2025Updated last year
- Implementation of SmoothCache, a project aimed at speeding-up Diffusion Transformer (DiT) based GenAI models with error-guided caching.☆48Jul 17, 2025Updated last year
- ☆13Mar 18, 2025Updated last year
- A repo for llm on ncnn☆15Jul 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.
- This is my CUDA optimization of OpenCV seamlessClone API at NORMAL_CLONE mode.☆10Oct 29, 2023Updated 3 years ago
- 🟣 Trie Data Structure interview questions and answers to help you prepare for your next data structures and algorithms interview in 2026…☆14Jan 4, 2026Updated 10 months ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆29Sep 4, 2025Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 9 months ago
- Optimizing diffusion for production-ready speeds☆41Jan 10, 2026Updated 10 months ago
- ☆173Mar 9, 2023Updated 3 years ago
- double_fpu_verilog☆22Jul 17, 2014Updated 12 years ago
Are these results useful?