- Seattle
- http:https://www.viirya.org
Block or Report
Block or report viirya
Contact GitHub support about this userโs behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
A massively parallel, high-level programming language
An extremely fast Python package installer and resolver, written in Rust.
Official implementation of Half-Quadratic Quantization (HQQ)
Apache DataFusion Comet Spark Accelerator
Distributed DataFrame for Python designed for the cloud, powered by Rust
A high-throughput and memory-efficient inference and serving engine for LLMs
๐ฆ A curated list of Rust tools, libraries, and frameworks for working with LLMs, GPT, AI
Distribute and run LLMs with a single file.
Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.
BtrBlocks: Efficient Columnar Compression for Data Lakes (SIGMOD 2023 Paper)
Apache Paimon is a lake format that enables building a Realtime Lakehouse Architecture with Flink and Spark for both streaming and batch operations.
LST-Bench is a framework that allows users to run benchmarks specifically designed for evaluating Log-Structured Tables (LSTs) such as Delta Lake, Apache Hudi, and Apache Iceberg.
A reference implementation of a Kubernetes scheduler written in Rust
๐ธ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Technical blogs around data collaboration, data management, and building collaborative applications.
Finetune ALL LLMs with ALL Adapeters on ALL Platforms!
Instruct-tune LLaMA on consumer hardware
๐ A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Sampling CPU and HEAP profiler for Java featuring AsyncGetCallTrace + perf_events
OpenLLaMA, a permissively licensed open source reproduction of Meta AIโs LLaMA 7B trained on the RedPajama dataset
๐ฆ๐ Build context-aware reasoning applications