Tag
Explore by tags
Provides a scalable physics-and-rendering simulation interface for robotics and embodied-AI research — unified multi-physics solvers, the Nyx renderer, and the Quadrants compiler. Runs from laptop to datacenter GPUs; suited for sensor-rich data generation and RL/robotics prototyping.
GPU-native physics engine unifying rigid-body, fluid, cloth, and deformable solvers in one Python framework for robotics and embodied-AI research. Built by a 20+ lab collaboration, now backed by Genesis AI, with generative tools to author 4D scenes.
Performs speaker diarization (who spoke when) with pyannote-audio: combines voice-activity detection, speaker-change and overlapped-speech detection to produce time-stamped speaker segments; compatible with Hugging Face Endpoints and ASR pipelines.
Provides a NumPy-like array framework for building and training ML on Apple silicon, with Python, C/C++, and Swift APIs plus PyTorch-style higher-level modules. Features lazy evaluation, composable AD/vectorization, and a unified-memory multi-device model so arrays can be used on CPU and GPU without explicit copies.
A selective State Space Model architecture and PyTorch implementation for linear-time sequence modeling. Hardware-aware, designed for information-dense tasks (e.g. language modeling), with pretrained weights on Hugging Face; requires CUDA-enabled PyTorch.
Provides a diffusion-model studio for image, video, audio-video, editing, LoRA, and full training workflows so many model families share one inference and training framework.
Builds custom AI inference servers in pure Python on top of FastAPI, keeping full control over request logic while batching, GPU autoscaling, streaming, and OpenAI-spec endpoints come built in. Claims a 2x+ throughput edge over plain FastAPI.
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.
Provides a PyTorch-native platform for experimenting with and scaling generative AI training, including composable parallelism, checkpointing, float8, logging, and Llama recipes.
Triton kernels and PyTorch layers for linear-attention, state-space, and sparse-attention token mixers (GLA, RWKV, Mamba2, GSA) as drop-in replacements for multihead attention. Runs on NVIDIA, AMD, and Intel GPUs with Hugging Face support.
Traces how Transformer LLMs route information from input to output, attributing each block's effect to individual attention heads and feed-forward neurons. Click any edge to see what a head promotes or suppresses in vocabulary space.
Serves large language and multimodal models with low latency and high throughput using RadixAttention, continuous batching, structured outputs, parallelism, quantization, and broad accelerator support.