Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.
Repository Index
111,821 visible repositories in the index
313–336 of 944 · 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
Boot large Ruby/Rails apps faster
- ruby
- performance
- gem
- computers
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
Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.
- knowledge-graph
- large-language-models
- retrieval-augmented-generation
- graphrag
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
Comprehensive resources on Generative AI, including a detailed roadmap, projects, use cases, interview preparation, and coding preparation.
[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
Awesome papers about unifying LLMs and KGs
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
MiniMax-M2, a model built for Max coding & agentic workflows.
A Python program to scrape secrets from GitHub through usage of a large repository of dorks.
This is literally a game framework, based on Unity game engine. It encapsulates commonly used game modules during development, and, to a large degree, standardises the process, enhances the development speed and ensures the product quality.
- game-frameworks
- game-modules
- game-development
- unity
Discussions about projects, technologies, and processes around building large-scale mobile apps
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
Apache Flume is a distributed, reliable, and available service for efficiently collecting, aggregating, and moving large amounts of log-like data
- flume
- java
- apache
- api
Fogsight is an AI agent and animation engine powered by Large Language Models.