xlite-dev

All

38 repositories

diffusers
Public
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
Python
•
Apache License 2.0
•6.3k•0•0•0•Updated Sep 16, 2025Sep 16, 2025
LeetCUDA
Public
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
cuda cuda-kernels cuda-demo cuda-toolkit cuda-library cuda-kernel learn-cuda cuda-cpp hgemm flash-attention
Cuda
•
GNU General Public License v3.0
•717•6.9k•8•0•Updated Sep 15, 2025Sep 15, 2025
HunyuanImage-2.1
Public
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation
Python
•
Other
•38•1•0•0•Updated Sep 10, 2025Sep 10, 2025
Wan2.2
Public
Wan: Open and Advanced Large-Scale Video Generative Models
Python
•
Apache License 2.0
•418•0•0•0•Updated Sep 9, 2025Sep 9, 2025
Qwen-Image-Lightning
Public
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
Python
•
Apache License 2.0
•28•0•0•0•Updated Sep 9, 2025Sep 9, 2025
cache-dit
Public
A Unified Cache Acceleration Toolbox for 🤗Diffusers: FLUX.1, Qwen-Image-Edit, Qwen-Image, Wan2.1/2.2, etc.
Python
•
Other
•9•4•0•0•Updated Sep 4, 2025Sep 4, 2025
Qwen-Image
Public
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
Python
•
Apache License 2.0
•265•1•0•0•Updated Sep 3, 2025Sep 3, 2025
comfyui-cache-dit
Public
cache-dit for comfyui
Python
•0•5•0•0•Updated Aug 26, 2025Aug 26, 2025
Awesome-DiT-Inference
Public
📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉
flux wan diffusion dit sora stable-diffusion sdxl sd15 deepcache open-sora-plan
Python
•
GNU General Public License v3.0
•19•403•0•0•Updated Aug 19, 2025Aug 19, 2025
Awesome-LLM-Inference
Public
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
mla vllm llm-inference awesome-llm flash-attention tensorrt-llm paged-attention deepseek flash-attention-3 deepseek-v3
Python
•
GNU General Public License v3.0
•306•4.5k•0•0•Updated Aug 19, 2025Aug 19, 2025
lite.ai.toolkit
Public
🛠A lite C++ AI toolkit: 100+ models with MNN, ORT and TRT, including Det, Seg, Stable-Diffusion, Face-Fusion, etc.🎉
tensorrt mnn ncnn onnx onnxruntime yolov5 tnn mnn-model yolox robustvideomatting
C++
•
GNU General Public License v3.0
•757•4.2k•0•0•Updated Aug 19, 2025Aug 19, 2025
ffpa-attn
Public
🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.
cuda attention sdpa mla mlsys tensor-cores flash-attention deepseek deepseek-v3 deepseek-r1
Cuda
•
GNU General Public License v3.0
•9•217•1•0•Updated Aug 8, 2025Aug 8, 2025
.github
Public
0•1•0•0•Updated Aug 8, 2025Aug 8, 2025
SpargeAttn
Public
SpargeAttention: A training-free sparse attention that can accelerate any model inference.
Cuda
•
Apache License 2.0
•56•6•0•0•Updated Aug 7, 2025Aug 7, 2025
SageAttention
Public
Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
Cuda
•
Apache License 2.0
•220•0•0•0•Updated Aug 6, 2025Aug 6, 2025
pytorch
Public
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Python
•
Other
•25k•0•0•0•Updated Aug 5, 2025Aug 5, 2025
flux
Public
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
C++
•
Apache License 2.0
•82•5•0•0•Updated Jul 30, 2025Jul 30, 2025
flux-faster
Public
A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.
flux flux-dev flux-fill flux-kontext flux-fast cache-dit
Python
•0•22•2•0•Updated Jul 18, 2025Jul 18, 2025
flux-fast
Public
A forked version of flux-fast that makes flux-fast even faster with cache-dit.
Python
•11•5•0•0•Updated Jul 18, 2025Jul 18, 2025
torchlm
Public
💎An easy-to-use PyTorch library for face landmarks detection: training, evaluation, inference, and 100+ data augmentations.🎉
heatmap regression pip data-augmentation face-landmarks mobilenet shufflenet torchvision albumentations yolov5
Python
•
MIT License
•25•265•15•0•Updated Jul 16, 2025Jul 16, 2025
nunchaku
Public
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Python
•
Apache License 2.0
•171•2•0•0•Updated Jul 14, 2025Jul 14, 2025
lihang-notes
Public
📚《统计学习方法-李航: 笔记》 200页PDF，公式细节讲解🎉
svm kd-tree ml statistics-learning lihang li-hang lihang-code lihang-notes li-hang-notes
Shell
•
GNU General Public License v3.0
•58•481•2•0•Updated Jul 13, 2025Jul 13, 2025
FlagGems
Public
FlagGems is an operator library for large language models implemented in the Triton Language.
Python
•
Apache License 2.0
•134•0•0•0•Updated Jul 11, 2025Jul 11, 2025
draft-attention
Public
Code for Draft Attention
Python
•2•1•0•0•Updated May 22, 2025May 22, 2025
HGEMM
Public
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
cuda tensor-cores hgemm
Cuda
•
GNU General Public License v3.0
•6•114•0•0•Updated May 10, 2025May 10, 2025
xlite-cli
Public
The cli version of lite.ai.toolkit
C++
•0•1•0•0•Updated Apr 9, 2025Apr 9, 2025
flashinfer
Public
FlashInfer: Kernel Library for LLM Serving
Cuda
•
Apache License 2.0
•500•0•0•0•Updated Mar 23, 2025Mar 23, 2025
tutorial-template
Public template
Template for the Read the Docs tutorial
Python
•1.5k•0•0•0•Updated Aug 9, 2024Aug 9, 2024
RVM-Inference
Public
🔥Robust Video Matting C++ inference toolkit with ONNXRuntime、MNN、NCNN and TNN, via lite.ai.toolkit.
cpp matting mnn ncnn onnx onnxruntime tnn robustvideomatting
C++
•
GNU General Public License v3.0
•27•133•20•0•Updated Jul 29, 2024Jul 29, 2024
netron-vscode-extension
Public
☕️ A vscode extension for netron, support *.pdmodel, *.nb, *.onnx, *.pb, *.h5, *.tflite, *.pth, *.pt, *.mnn, *.param, etc.
deeplearning paddle mnn ncnn onnx onnxruntime yolov5 tnn netron yolov8
TypeScript
•
Other
•0•14•3•0•Updated Jun 4, 2023Jun 4, 2023