FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Hierarchical Reasoning Model Official Release

GLM-4.5: An open-source large language model designed for intelligent agents by Z.ai

FAIR Sequence Modeling Toolkit 2

Open-source unified multimodal model

Official Codes for our CVPR paper <CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering>

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

所有小初高、大学PDF教材。

Prompts for our Grok chat assistant and the `@grok` bot on X.

Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling

A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms

Mcity Data Engine

MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

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

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Lla…

Pretraining and inference code for a large-scale depth-recurrent language model

This is the repo for the survey of LLM4IR.

Large Language Model-enhanced Recommender System Papers

A list of awesome papers and resources of recommender system on large language model (LLM).

Paper List for Recommend-system PreTrained Models

Recommender systems with large language models (Paper list)

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

Scalable and memory-optimized training of diffusion models

Build Real-Time Knowledge Graphs for AI Agents

[NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

Large Language Model (LLM) Systems Paper List

Lets make video diffusion practical!