AI Deploy2023
Open-source LLM inference and serving engine built around PagedAttention, which manages the KV cache like OS virtual memory to cut waste and raise throughput. Supports continuous batching, KV cache sharing, quantization, and an OpenAI-compatible API.
AI Infra2023
Probes LLMs for failure modes — prompt injection, jailbreaks, data leakage, toxicity, hallucination — the way nmap scans a network. Ships 20+ attack probes that run against Hugging Face, OpenAI, Bedrock, Cohere, or any REST endpoint.
AI Audio2023
Terminal CLI for on-device Whisper ASR using Hugging Face Transformers + Optimum, with optional Flash Attention 2, batching, and diarization support — focused on high-throughput transcription on NVIDIA GPUs and Apple Silicon (mps).
AI Deploy2023
Compiles LLMs into optimized TensorRT inference engines for NVIDIA GPUs via a Python API. Layers in kernel fusion, quantization, paged attention, KV caching, and continuous in-flight batching, scaling from a single GPU to multi-node deployments.
AI Model2023
Estimates and tracks 6D poses of novel objects without per-object fine-tuning — supports both model-based (CAD) and model-free (few reference images) setups. Trained on large-scale synthetic data with a transformer-based architecture and contrastive learning; CVPR 2024 highlight with demos and pretrained weights.
AI Infra2024
Chains pre-trained AI weather and climate models like GraphCast, Pangu, and FourCastNet into composable inference pipelines. Swap prognostic or diagnostic components, plug in reanalysis sources, and add ensemble perturbations or in-loop metrics.
AI Model2024
A research codebase and model family for vision–language models that experiments with data‑centric post‑training strategies and long‑context multimodal reasoning. Includes model reports, released research weights (non‑commercial), grounding tools (LocateAnything) and integrations for inference/optimization.
Embodied AI2024
GPU‑accelerated framework for training physically simulated humanoid characters and robots using reinforcement learning and motion imitation. Provides a modular multi‑backend simulator stack, large‑scale multi‑GPU training recipes, built‑in motion retargeting and an ONNX deployment pathway to real robots.
AI Infra2024
Lets Python developers write tile-based parallel kernels for NVIDIA GPUs, generating CUDA Tile IR while staying close to Python syntax for custom GPU operations.
AI Infra2024
A compact domain-specific language for writing high-performance GPU/CPU kernels (GEMM, FlashAttention, sparse kernels) with Python-like syntax. It provides tiling/pipelining primitives, a TVM-based compiler and multiple backends (CUDA/CuTeDSL, NVRTC, WebGPU, Metal, Ascend) for operator-level performance work.
AI Model2024
High-resolution image and video generation codebase and models that run with far lower compute and memory than typical diffusion systems. Uses linear-attention DiT variants, aggressive latent compression, and inference-scaling to support text-to-image (up to 4K), fast one/few-step generation, and efficient video pipelines.
Embodied AI2024
Agentive operating system for physical robots that lets developers compose agent-native modules in Python to connect perception, spatial memory, and control across humanoids, quadrupeds, drones, and simulators.