Starred repositories
ComfyUI's ControlNet Auxiliary Preprocessors
A convenient and user-friendly anime-style image data processing library that integrates various advanced anime-style image processing models
Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.
🚀 Efficient implementations of state-of-the-art linear attention models
slime is an LLM post-training framework for RL Scaling.
Ring attention implementation with flash attention
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
fanshiqing / grouped_gemm
Forked from tgale96/grouped_gemmPyTorch bindings for CUTLASS grouped GEMM.
Machine Learning Engineering Open Book
Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.
Ongoing research training transformer models at scale
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
watchpoints is an easy-to-use, intuitive variable/object monitor tool for python that behaves similar to watchpoints in gdb.
A library that can print Python objects in human readable format
coredumpy saves your crash site for post-mortem debugging
An intuitive and low-overhead instrumentation tool for Python
A debugging and profiling tool that can trace and visualize python code execution
Tensors and Dynamic neural networks in Python with strong GPU acceleration
[CVPR2024, Highlight] Official code for DragDiffusion
[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Repository for ECCVW 2024 paper "Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation"
Papers, datasets, and resources related to 2D cartoon video research. Contributions welcome.
🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.