Repositories

BlinkDL repositories

36 supported repositories

Path tracing demo with JS in your web browser. 用浏览器JS做路径跟踪渲染。

Last commit Jun 11, 2018

 (7 stars) (2 forks) (0 indexed issues) (0 open good first issues)

Project Ivory is a simple forum written a few years ago.

Last commit May 16, 2020

 (0 stars) (0 forks) (0 indexed issues) (0 open good first issues)

The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

Last commit Dec 10, 2025

 (234 stars) (35 forks) (0 indexed issues) (0 open good first issues)

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Last commit Aug 14, 2026

 (14,665 stars) (1,019 forks) (0 indexed issues) (0 open good first issues)

RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.

Last commit Sep 14, 2022

 (67 stars) (19 forks) (0 indexed issues) (0 open good first issues)

Last commit Aug 11, 2026

 (14 stars) (8 forks) (0 indexed issues) (0 open good first issues)

LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence

Last commit Feb 21, 2022

 (61 stars) (4 forks) (0 indexed issues) (0 open good first issues)

My vibe math results

Last commit Aug 16, 2026

 (5 stars) (2 forks) (0 indexed issues) (0 open good first issues)

Let us make Psychohistory (as in Asimov) a reality, and accessible to everyone. Useful for LLM grounding and games / fiction / business / finance / governance, and can align agents with human too.

Last commit Apr 9, 2023

 (40 stars) (1 fork) (0 indexed issues) (0 open good first issues)

Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.

Last commit Feb 2, 2025

 (73 stars) (2 forks) (0 indexed issues) (0 open good first issues)

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Last commit Feb 25, 2022

 (0 stars) (0 forks) (0 indexed issues) (0 open good first issues)

LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training

Last commit Sep 5, 2022

 (0 stars) (2 forks) (0 indexed issues) (0 open good first issues)
BlinkDL/minGPT-tunedJupyter Notebook

A *tuned* minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Last commit Aug 9, 2021

 (118 stars) (11 forks) (0 indexed issues) (0 open good first issues)

RWKV-7: Surpassing GPT

Last commit Nov 17, 2024

 (104 stars) (10 forks) (0 indexed issues) (0 open good first issues)

RWKV in nanoGPT style

Last commit Dec 12, 2023

 (200 stars) (10 forks) (0 indexed issues) (0 open good first issues)

Understand and test language model architectures on synthetic tasks.

Last commit Jun 8, 2025

 (11 stars) (0 forks) (0 indexed issues) (0 open good first issues)