Robust Speech Recognition via Large-Scale Weak Supervision

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

Low-code framework for building custom LLMs, neural networks, and other AI models

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Interactive HTML BOM generation plugin for KiCad, EasyEDA, Eagle, Fusion360 and Allegro PCB designer

"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

RayLLM - LLMs on Ray

Curate better data for LLMs

Landmark Attention: Random-Access Infinite Context Length for Transformers

Landmark Attention: Random-Access Infinite Context Length for Transformers QLoRA

Instruct-tune Open LLaMA / RedPajama / StableLM models on consumer hardware using QLoRA

A python library to write gerber files