Pinned Loading

1. nanoplm nanoplm Public

   Forked from peymanvahidi/nanoplm

   Dev fork of nanoplm, with focus on throughput and arch optimizations in pretraining.

   Python 1

2. flash-mHC flash-mHC Public

   Fast implementation of manifold-constrained hyperconnections in Triton.

   Python

3. nanogpt-fp8 nanogpt-fp8 Public

   Nanochat inspired LLM pretraining using Transformer-Engine with MXFP8 and NVFP4 support. Up to 30% faster than nanochat

   Python 5 2

4. matmul_assembly_x86 matmul_assembly_x86 Public

   Hyper-optimized FP32 GEMM kernels in handwritten AVX2 ASM with a worklog of optimizations implemented

   Assembly 4

5. llm.c llm.c Public

   Forked from karpathy/llm.c

   3x faster LLM training on CPU than Karpathy's original repo

   Cuda 1

6. Candles-ProbCheck Candles-ProbCheck Public

   Simple notebook to check probability of every pair of candlesticks in a day being of the same or opposite color in a given period of time

   Jupyter Notebook