a (nearly) no-CSS, fast, minimalist Hugo theme ported from riggraz/no-style-please.

Open Agentic Schema Framework

The slightly more awesome standard unix password manager for teams

Read-only demo server for larger datasets

📚A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism etc.

FlashInfer: Kernel Library for LLM Serving

Build computation graphs from python functions

A computation graph micro-framework providing seamless lazy and concurrent evaluation

Documentation for Google's Gen AI site - including the Gemini API and Gemma

Dynamic Memory Management for Serving LLMs without PagedAttention

O1 Replication Journey

CUDA on non-NVIDIA GPUs

NumPy & SciPy for GPU

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…

MSCCL++: A GPU-driven communication stack for scalable AI applications

AICI: Prompts as (Wasm) Programs

Read-only mirror of https://git.zx2c4.com/cgit/about . Pull requests and issues on GitHub cannot be accepted and will be automatically closed. The proper way to submit changes is via the mailing li…

Inference Llama 2 in one file of pure C

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

Altis-SYCL: a SYCL-based implementation of the Altis GPGPU benchmark suite for CPUs, GPUs, and FPGAs.

A High contrast, text oriented, performant and Javascript-free theme for Hugo.

A simple, responsive writing (and reading) theme for Hugo.

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

system paper reading notes

📖 A curated list of resources dedicated to Machine Learning for Systems research

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

This repository contains demos I made with the Transformers library by HuggingFace.