Popular repositories

1. aegis aegis Public

   Self-hardening firewall for large language models

   Python 243 6

2. trex trex Public

   Enforce structured output from LLMs 100% of the time

   Python 238 9

3. bitsandbytes bitsandbytes Public

   Forked from TimDettmers/bitsandbytes

   8-bit CUDA functions for PyTorch

   Python 1

4. llama_index llama_index Public

   Forked from run-llama/llama_index

   LlamaIndex (GPT Index) is a data framework for your LLM applications

   Python

5. FastCkpt FastCkpt Public

   Forked from RulinShao/FastCkpt

   Python package for rematerialization-aware gradient checkpointing

   Python

6. flash-attention flash-attention Public

   Forked from Dao-AILab/flash-attention

   Fast and memory-efficient exact attention

   Python