jamesparsloe

jamesparsloe's Stars

• karpathy/nano-llama31

  nanoGPT style version of Llama 3.1

  Language:Python1.2k56

• meta-llama/llama-stack

  Model components of the Llama Stack APIs

  Language:Python2.1k218

• EleutherAI/nanoGPT-mup

  The simplest, fastest repository for training/finetuning medium-sized GPTs.

  Language:Python573

• QwenLM/Qwen2.5

  Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

  Language:Shell8.5k524

• pytorch-labs/LeanRL

  LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

  Language:Python3469

• leerob/next-saas-starter

  Get started quickly with Next.js, Postgres, Stripe, and shadcn/ui.

  Language:TypeScript4.4k464

• apple/ml-sigmoid-attention

  Language:Python2139

• midday-ai/v1

  An open-source starter kit based on Midday.

  Language:TypeScript2.9k240

• Cinnamon/kotaemon

  An open-source RAG-based tool for chatting with your documents.

  Language:Python12.5k936

• linkedin/Liger-Kernel

  Efficient Triton Kernels for LLM Training

  Language:Python3.1k158

• All-Hands-AI/OpenHands

  🙌 OpenHands: Code Less, Make More

  Language:Python32.2k3.7k

• microsoft/autogen

  A programming framework for agentic AI 🤖

  Language:Jupyter Notebook31.3k4.6k

• cohere-ai/cohere-terrarium

  A simple Python sandbox for helpful LLM data agents

  Language:Python14322

• chrxh/alien

  ALIEN is a CUDA-powered artificial life simulation program.

  Language:C++4.6k137

• beam-cloud/beta9

  Run GPU Workloads Across Multiple Clouds

  Language:Go40118

• sustcsonglin/flash-linear-attention

  Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

  Language:Python1.2k66

• EleutherAI/cookbook

  Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

  Language:Python67633

• facebookresearch/segment-anything-2

  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

  Language:Jupyter Notebook11.1k940

• pytorch-labs/attention-gym

  Helpful tools and examples for working with flex-attention

  Language:Python36415

• UKGovernmentBEIS/inspect_ai

  Inspect: A framework for large language model evaluations

  Language:Python55893

• pytorch/tensordict

  TensorDict is a pytorch dedicated tensor container.

  Language:Python81366

• black-forest-labs/flux

  Official inference repo for FLUX.1 models

  Language:Python14.2k1k

• aiola-lab/whisper-medusa

  Whisper with Medusa heads

  Language:Python78248

• ax-llm/ax

  The unofficial DSPy framework. Build LLM powered Agents and "Agentic workflows" based on the Stanford DSP paper.

  Language:TypeScript1k69

• pytorch/torchchat

  Run PyTorch LLMs locally on servers, desktop and mobile

  Language:Python3.2k197

• flashinfer-ai/flashinfer

  FlashInfer: Kernel Library for LLM Serving

  Language:Cuda1.2k109

• neondatabase/neon

  Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.

  Language:Rust14.5k419

• meta-llama/llama-stack-apps

  Agentic components of the Llama Stack APIs

  Language:Python3.6k387

• dubinc/dub

  Open-source link management infrastructure. Loved by modern marketing teams like Vercel, Raycast, and Perplexity.

  Language:TypeScript17.8k1.9k

• lucidrains/rectified-flow-pytorch

  Implementation of rectified flow and some of its followup research / improvements in Pytorch

  Language:Python1602