Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.
Repository Index
111,085 visible repositories in the index
169–192 of 454 · Most stars
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
- kv-cache
- llm-inference
- local-llm
- quantization
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- low-precision
- pruning
- sparsity
- auto-tuning
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
- cross-modal-learning
- cross-modality
- deep-learning
- language-model
[ICCV2025] LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
- aicg
- aigc
- digitalhuman
Project Page for "LISA: Reasoning Segmentation via Large Language Model"
- large-language-model
- llm
- multi-modal
- segmentation
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
- fine-tuning-llm
- large-language-models
- long-context
- llm
The largest Awesome Curated list of command line programs (CLI/TUI) with source data organized into CSV files
[EMNLP-2024] Build multimodal language agents for fast prototype and production
- large-language-models
- multimodal-agent
- vision-and-language
- agent
[ECCV 2018] CCPD: a diverse and well-annotated dataset for license plate detection and recognition
- plate-detection
- ccpd
- dataset
- detection
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
- ai-agent
- ai-agents-framework
- computer-control
- cradle
A Python program to scrape secrets from GitHub through usage of a large repository of dorks.
Awesome Reasoning LLM Tutorial/Survey/Guide
- fine
- large-language-models
- post-training
- reasoning
🥂 Gracefully face hCaptcha challenge with multimodal large language model.
- hcaptcha
- hcaptcha-solver
- yolo
- playwright
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
- large-language-models
- llm-inference
- speculative-decoding
使用AI大模型,一键生成高清故事短视频。Generate high-definition story short videos with one click using AI large models.
✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
- large-multimodal-models
- multimodal-large-language-models
- omni-language-model
- omni-modal-video-understanding
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
- deep-learning
- flax
- jax
- language-model
A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.
A simple, performant, and scalable Jax LLM!
Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc. 开源大模型的统一后端接口
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
- llm-agents
- llm-training
- reinforcement-learning
- large-language-models
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
- chart-understanding
- document-understanding
- mllm
- multimodal