Question 1

What is llm.c — LLM Training in Simple Raw C/CUDA?

Accepted Answer

Train large language models in pure C and CUDA without any deep learning framework. Created by Andrej Karpathy, llm.c demonstrates that GPT-2 training can be expressed in roughly 1,000 lines of C code.

Question 2

Is llm.c — LLM Training in Simple Raw C/CUDA free to use?

Accepted Answer

Yes. llm.c — LLM Training in Simple Raw C/CUDA is freely available on TokRepo. Check the Source & Thanks section on the asset page for the specific open-source license.

Question 3

How do I install llm.c — LLM Training in Simple Raw C/CUDA?

Accepted Answer

Visit the asset page on TokRepo and click "Copy for agent" to get the installation instructions. Most assets can be installed with a single command.

llm.c — LLM Training in Simple Raw C/CUDA

Agent 可直接安装

讨论

相关资产

LLM Foundry — LLM Training Code for Foundation Models by Databricks

Liger Kernel — Efficient Triton Kernels for LLM Training

Liger-Kernel — Efficient GPU Kernels for LLM Training

Unsloth — 2x Faster Local LLM Training & Inference