Luis Chamberlain

R&D on NLP

AI: Post Transformers podcast software

A high-throughput and memory-efficient inference and serving engine for LLMs

Memory-Traffic Saturation in Autoregressive Transformer Decode

My fork of mbsync

A collection of visualizations

KV cache visualizations

No description provided.

Central Regulatory Domain Agent

The trackio-view pypi trackio package for visualization enhancements on the console

Low-Level Graph Neural Network Operators for PyG

A proposal for a unified GPU compute driver on Linux

Why is attention low rank

This is a repository contaning baseline code for DGraphFin Dataset

QCA swiss army knife

Bare bones kconfig kick off project

Console mutlti-gpu monitoring tool

Neural network experimentations

peace

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Test BPE

View star details on the console

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Set of GPU tests

demos vllm integration results on kdevops on bare metal

minio WAF

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

demo nfstests results

demo pynfs tests

A lightweight, local-first, and free experiment tracking library from Hugging Face 🤗