Cookize

Cookize's Stars

• yoziru/nextjs-vllm-ui

  Fully-featured, beautiful web interface for vLLM - built with NextJS.

  Language:TypeScript6312

• philipperemy/keract

  Layers Outputs and Gradients in Keras. Made easy.

  Language:Python1k185

• AILab-CVC/YOLO-World

  [CVPR 2024] Real-Time Open-Vocabulary Object Detection

  Language:Python4.7k453

• jtpio/ipylab

  Control JupyterLab from Python Notebooks with Jupyter Widgets 🧪 ☢️ 🐍

  Language:TypeScript19613

• fudan-generative-vision/champ

  Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

  Language:Python4.7k598

• lllyasviel/ControlNet-v1-1-nightly

  Nightly release of ControlNet 1.1

  Language:Python4.7k375

• showlab/Awesome-Video-Diffusion

  A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.

  3.4k200

• hpcaitech/Open-Sora

  Open-Sora: Democratizing Efficient Video Production for All

  Language:Python22.3k2.2k

• jax-ml/jax

  Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

  Language:Python30.5k2.8k

• LargeWorldModel/LWM

  Large World Model -- Modeling Text and Video with Millions Context

  Language:Python7.2k552

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8.7k990

• THUDM/LongBench

  [ACL 2024] LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

  Language:Python66354

• jondurbin/bagel

  A bagel, with everything.

  Language:Python31231

• drewlinsley/pathfinder

  Language:Python64

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python14.3k1.3k

• leanprover/lean4

  Lean 4 programming language and theorem prover

  Language:Lean4.7k424

• kaarthik108/snowChat

  Chat snowflake - Text to SQL

  Language:Python452257

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python30.3k4.6k

• thu-coai/Safety-Prompts

  Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

  87081

• EleutherAI/gpt-neox

  An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

  Language:Python6.9k1k

• IDEA-CCNL/GTS-Engine

  GTS Engine: A powerful NLU Training System。GTS引擎（GTS-Engine）是一款开箱即用且性能强大的自然语言理解引擎，聚焦于小样本任务，能够仅用小样本就能自动化生产NLP模型。

  Language:Python899

• huggingface/deep-rl-class

  This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.

  Language:MDX3.9k602

• probml/pml2-book

  Probabilistic Machine Learning: Advanced Topics

  1.4k119

• zeekay/flask-uwsgi-websocket

  🔌 High-performance WebSockets for your Flask apps powered by uWSGI.

  Language:Python27260

• thunlp/CLAIM

  7949

• triton-inference-server/python_backend

  Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

  Language:C++548145

• NVIDIA/Megatron-LM

  Ongoing research training transformer models at scale

  Language:Python10.6k2.4k

• Oldpan/Pytorch-Memory-Utils

  pytorch memory track code

  Language:Python1k155

• IDEA-CCNL/Fengshenbang-LM

  Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

  Language:Python4k376

• IDEA-CCNL/fs_datasets

  Language:Python111