- New York, New York
Highlights
- Pro
Lists (1)
Sort Name ascending (A-Z)
Stars
high-performance linear attention kernel library built on TileLang
The official implementation for paper "AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation"
A Datacenter Scale Distributed Inference Serving Framework
Warp is an agentic development environment, born out of the terminal.
Post-training scripts and samples for NVIDIA Cosmos ecosystem
A Python DSL to write Nvidia PTX for Hopper and Blackwell in JAX and PyTorch
WORKBank Database derived from large-scale audit of worker desire and technological capability of AI agents for work.
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.
a toolkit on knowledge distillation for large language models
A high-performance toolkit for atomistic simulations in JAX.
RoboChem-Flex is a low-cost, modular self-driving laboratory platform designed to democratize autonomous chemical experimentation.
Lightweight harness for replaying inference traffic against an endpoint
Desktop app to manage markdown knowledge bases
Official implementation of Paper "System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving"
togethercomputer / ssd
Forked from tanishqkumar/ssdA lightweight inference engine supporting speculative speculative decoding (SSD).
High accuracy RAG for answering questions from scientific documents with citations
Visualize harmony chat data and codex sessions in your browser
FlashKDA: high-performance Kimi Delta Attention kernels
A Foundational Evolving Agent Framework for Agentic Science at Scale.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Biomni: a general-purpose biomedical AI agent
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…