Pinned Loading

1. efficient-llm-finetuning efficient-llm-finetuning Public

   Efficient LLM fine-tuning & deployment: LoRA, QLoRA, PTQ and QAT — with benchmarking and config-driven pipelines.

   Python 3

2. llm-inference-engine llm-inference-engine Public

   A from scratch LLM inference engine build in PyTorch with custom GPT2 transformers, kv cache, paged kv cache, continuous batching and A100 benchmarks

   Python 4 2

3. tinystories-transformer-training tinystories-transformer-training Public

   Decoder-only Transformer trained from scratch with token-based stopping, optimizer & scheduler ablations

   Python

4. nn-from-scratch-numpy nn-from-scratch-numpy Public

   This repo contains MLP implementation from scratch using numpy

   Python