FlashKDA: high-performance Kimi Delta Attention kernels
☆447May 26, 2026Updated 2 weeks ago
Alternatives and similar repositories for FlashKDA
Users that are interested in FlashKDA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated 10 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆105Apr 7, 2026Updated 2 months ago
- ☆52May 19, 2025Updated last year
- Open-source toolkit for training, Priming, and serving next generation Hybrid architectures☆71May 9, 2026Updated 3 weeks ago
- ☆57Feb 24, 2026Updated 3 months ago
- 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.
- Composable and Embeddable Communication Runtime for Distributed AI Services☆101Updated this week
- Official repository Flash Local Linear Attention☆36May 28, 2026Updated last week
- ☆40Dec 14, 2025Updated 5 months ago
- This repository contains companion software for the Colfax Research paper "Categorical Foundations for CuTe Layouts".☆135Sep 24, 2025Updated 8 months ago
- ☆66Feb 15, 2026Updated 3 months ago
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆518Updated this week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆24Updated this week
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆61Feb 6, 2026Updated 4 months ago
- My submission for the GPUMODE/AMD fp8 mm challenge☆29Jun 4, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆193May 22, 2026Updated 2 weeks ago
- Learning TileLang with 10 puzzles!☆314May 28, 2026Updated last week
- semantic tokenizer for speech and music☆21Jul 6, 2025Updated 11 months ago
- A practical way of learning Swizzle☆41Feb 3, 2025Updated last year
- A std::execution style runtime context and High Performance RPC Transport for using OpenUCX. Including CUDA/ROCM/... devices with RDMA.☆32May 26, 2026Updated 2 weeks ago
- ☆32Jul 2, 2025Updated 11 months ago
- Exploring how optimizations for GEMMs work☆36Feb 28, 2026Updated 3 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 10 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆192Feb 11, 2026Updated 3 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆14Nov 3, 2025Updated 7 months ago
- Matrix multiplication on GPUs for matrices stored on a CPU. Similar to cublasXt, but ported to both NVIDIA and AMD GPUs.☆32Apr 2, 2025Updated last year
- Stable Diffusion in TensorRT 8.5+☆15Mar 19, 2023Updated 3 years ago
- Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.☆18Jan 15, 2025Updated last year
- Transformers components but in Triton☆34May 9, 2025Updated last year
- Helpful kernel tutorials, examples and SKILLs for tile-based GPU programming☆745Jun 2, 2026Updated last week
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆52Jul 4, 2025Updated 11 months ago
- High-performance LLM operator library built on TileLang.☆130Updated this week
- Bert TensorRT模型加速部署☆10Apr 1, 2022Updated 4 years ago
- 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.
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 4 months ago
- ☆11Apr 5, 2021Updated 5 years ago
- A toolkit for developers to simplify the transformation of nn.Module instances. It's now corresponding to Pytorch.fx.☆13Apr 7, 2023Updated 3 years ago
- LoRAFusion: Efficient LoRA Fine-Tuning for LLMs☆27Apr 8, 2026Updated 2 months ago
- ☆66Apr 26, 2025Updated last year
- Debug print operator for cudagraph debugging☆15Aug 2, 2024Updated last year
- ☆33Dec 31, 2025Updated 5 months ago