CroissAttn: FP4 attention forward and backward, with analysis of stochastic rounding, zero-sum softmax gradients, and sampled centering.
☆15Oct 25, 2026Updated last week
Alternatives and similar repositories for fp4Attn
Users that are interested in fp4Attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆41Oct 5, 2026Updated 3 weeks ago
- Rust bindings for the [3FS USRBIO API](https://github.com/deepseek-ai/3FS/blob/main/src/lib/api/UsrbIo.md).☆11Oct 20, 2026Updated last week
- The ultimate Udoo library that allows you to use the linux side as a library, just like a shield for the Sam3x!☆10Nov 19, 2023Updated 2 years ago
- W4A16 MoE GEMM CUDA kernel. Tuned for H200, B200 & B300.☆14Updated this week
- MACE is A C++ Engine☆10Dec 9, 2019Updated 6 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Native WebVR for node☆10Dec 31, 2017Updated 8 years ago
- Breaking the quadratic memory barrier in AI☆60Oct 13, 2026Updated 2 weeks ago
- A RAG system that attempts to eliminate relationship hallucinations by fusing a knowledge graph with a vector DB and prioritizing knowled…☆10Apr 10, 2026Updated 6 months ago
- Network link monitor daemon☆13Mar 29, 2016Updated 10 years ago
- S3 Upload plugin for PyUpdater☆12Dec 7, 2021Updated 4 years ago
- ☆10Mar 27, 2018Updated 8 years ago
- A CUDA implementation of the Parallel Median of Medians kth element algorithm☆12Jan 29, 2012Updated 14 years ago
- Made for the academy high school management system☆11May 21, 2016Updated 10 years ago
- Repo containing the training and inference code for 'Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting.'☆16May 2, 2026Updated 5 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official code base for la LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels extended to also learn late…☆15Apr 9, 2026Updated 6 months ago
- Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.☆24Oct 21, 2026Updated last week
- Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention☆83Apr 7, 2026Updated 6 months ago
- VideoAtlas/VideoRLM: Navigating Long-Form Video in Logarithmic Compute☆21May 19, 2026Updated 5 months ago
- ALIKED LightGlue ONNX inference☆19Feb 21, 2025Updated last year
- Apple Silicon (Metal) backend for Triton: write standard @triton.jit kernels on your Mac GPU. The same source runs bit-identical on NVIDI…☆26Sep 17, 2026Updated last month
- Stein Variational Gradient Descent with Matrix-Valued Kernels☆13Dec 4, 2019Updated 6 years ago
- ☆79Oct 18, 2026Updated last week
- [ICML 2025] Differentiable Solver Search for Fast Diffusion Sampling☆21Jul 7, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆27Jul 13, 2026Updated 3 months ago
- ☆11Updated this week
- ☆15Jul 14, 2026Updated 3 months ago
- Surgical GPU kernel benchmark: 7 hard problems, frontier coding agents, roofline-graded against hardware peak.☆19Jun 12, 2026Updated 4 months ago
- ☆12May 8, 2026Updated 5 months ago
- A friendly onboarding wizard for Plasma☆11Updated this week
- ☆25May 22, 2026Updated 5 months ago
- Next-gen Rust diagram engine: 32 Mermaid-compatible diagram types, 18 layout algorithms plus Auto, intent-aware error recovery, determini…☆61Updated this week
- ☆16Aug 26, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- fast Eg-walker inspired collaborative text algorithm☆42Oct 23, 2026Updated last week
- [CVPR2026] LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories☆61Jun 13, 2026Updated 4 months ago
- Implementation for the paper 'Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport' (ICL…☆23Jan 1, 2025Updated last year
- Artifacts for SWARM: Replicating Shared Disaggregated-Memory Data in No Time☆10Sep 25, 2024Updated 2 years ago
- [CVPR 2026] CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning☆17May 15, 2026Updated 5 months ago
- 面向多平台编译优化的深度学习中间表示☆10Oct 28, 2024Updated 2 years ago
- Optimized cross-platform expansion of autoresearch.☆18Mar 23, 2026Updated 7 months ago