DeepEP: an efficient expert-parallel communication library

Skatteverket Tax Scripts

GTKWave is a fully featured GTK+ based wave viewer for Unix and Win32 which reads LXT, LXT2, VZT, FST, and GHW files as well as standard Verilog VCD/EVCD files and allows their viewing.

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

The gem5 Bootcamp 2022 environment. Archived.

Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)

Libtpa(Transport Protocol Acceleration), a DPDK based userspace TCP stack implementation.

A quick guide (especially) for trending instruction finetuning datasets

Master programming by recreating your favorite technologies from scratch.

Fine-tune SantaCoder for Code/Text Generation.

A framework for few-shot evaluation of language models.

Sparsity-aware deep learning inference runtime for CPUs

Self-evaluating interview for AI coders

Run evaluation on LLMs using human-eval benchmark

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Minimal code to train a Large Language Model (LLM).

A simple and effective LLM pruning approach.

BertViz: Visualize Attention in Transformer Models

Learn where some of the network sysctl variables fit into the Linux/Kernel network flow. Translations: 🇷🇺

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

LLM inference in C/C++

Reverse engineered ChatGPT API

🤖🌊 aiFlows: The building blocks of your collaborative AI

Universal and Transferable Attacks on Aligned Language Models

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.