xuanhan863

Slice's starred repositories

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Language:PythonApache-2.015902 105 820

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonBSD-3-Clause5536 63 98

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

Language:PythonMIT4473 58 152

SuGaR

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

Language:C++NOASSERTION2133 64 212

segment-anything-fast

A batched offline inference oriented version of segment-anything

Language:PythonApache-2.01186 10 44

stable-fast

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Language:PythonMIT1152 18 122

PatchFusion

[CVPR 2024] An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation

Language:PythonMIT953 23 40

3D-LLM

Code for 3D-LLM: Injecting the 3D World into Large Language Models

Language:PythonMIT907 16 62

genmusic_demo_list

a list of demo websites for automatic music generation research

603 33 7

ziplora-pytorch

Implementation of "ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs"

Language:PythonMIT504 11 19

tokenize-anything

[ECCV 2024] Tokenize Anything via Prompting

Language:Jupyter NotebookApache-2.0502 6 16

quip-sharp

Language:PythonGPL-3.0482 11 61

glake

GLake: optimizing GPU memory management and IO transmission.

Language:PythonApache-2.0352 7 22

PoseAnything

A Graph-Based Approach for Category-Agnostic Pose Estimation [ECCV 2024]

Language:PythonApache-2.0303 4 10

ml-sigma-reparam

Language:PythonNOASSERTION288 130

Pengi

An Audio Language model for Audio Tasks

Language:PythonMIT281 14 13

DepthFlow

🌊 Image to → 2.5D Parallax Effect Video. A Free and Open Source ImmersityAI alternative

Language:PythonAGPL-3.0210 7 29

Diff-HierVC

Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"

Language:Python188 15 7