Pinned Loading

1. LLM-accelerator LLM-accelerator Public

   C++ 2

2. Bitnet-C-benchmark Bitnet-C-benchmark Public

   Single-thread, end-to-end C++ implementation of the Bitnet (1.58-bit weight) model

   C++ 1

3. cornell-zhang/allo cornell-zhang/allo Public

   Allo: A Programming Model for Composable Accelerator Design

   Python 145 28

4. pytorch-labs/gpt-fast pytorch-labs/gpt-fast Public

   Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

   Python 5.7k 514

5. ggerganov/llama.cpp ggerganov/llama.cpp Public

   LLM inference in C/C++

   C++ 67.8k 9.7k

6. mobiusml/hqq mobiusml/hqq Public

   Official implementation of Half-Quadratic Quantization (HQQ)

   Python 696 68