Popular repositories Loading

1. TransformerEngine TransformerEngine Public

   Forked from NVIDIA/TransformerEngine

   A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…

   Python

2. llm-systems-from-scratch llm-systems-from-scratch Public

   A small Llama-style LLM training + inference stack, optimized one measured bottleneck at a time.

   Python