Results for "gpu"

GPU DataFrame library from RAPIDS. Accelerates Pandas workflows on NVIDIA GPUs with zero code changes using cuDF.pandas accelerator mode.

Flexible framework for heterogeneous CPU-GPU LLM inference and fine-tuning. Enables running large MoE models by offloading experts to CPU with BF16/FP8 precision support.

Similarity search and clustering library for dense vectors with CPU and GPU implementations.

Infrastructure automation tools for building GPU clusters with Kubernetes and Slurm. Deploys multi-node GPU clusters with monitoring, logging, and storage for AI/HPC workloads. BSD-3-Clause licensed.

High-speed LLM inference for local deployment on consumer GPUs. Achieves up to 11x speedup over llama.cpp on RTX 4090 by exploiting power-law neuron activation patterns. MIT licensed.

Kubernetes-native GPU scheduler for AI workloads at large scale. Originally developed by Run:ai, now open-sourced by NVIDIA. Optimizes GPU resource allocation with dynamic allocation and efficient queue management. Apache 2.0 licensed.

GPU cluster manager that orchestrates inference engines like vLLM and SGLang. Automated engine selection, parameter optimization, and distributed multi-GPU deployment for high-performance AI workloads.

100% pure-Julia ML stack with lightweight abstractions on top of native GPU and AD support. Elegant, hackable, and fully integrated with Julia's scientific computing ecosystem.

GPU graph analytics library with NetworkX-compatible API. 10-100x faster than CPU for large-scale graph algorithms. Apache 2.0 licensed.

Checkpoint/restore for vLLM that packages a warmed-up engine (processes, GPU state with CUDA graphs, processed weights; 1–8 GPUs on one node) as an OCI artifact and restores it in seconds on hosts with the same GPUs and driver branch.

Dynamic computation graphs, Pythonic API, dominant in research and production. The current standard for most frontier AI work.

CLI that health-checks NVIDIA GPU nodes against reference values for the same model (power limit, sustained clocks, BF16 TFLOPS, memory bandwidth, throttle reasons, PCIe, ECC), with a per-minute watch mode for rentals. MIT licensed.

NumPy and SciPy-compatible array library for GPU-accelerated computing in Python.

Compiler that fuses model execution into a single mega-kernel for tighter performance.

Single-GPU 70B inference stack with strong memory/performance optimizations for local deployment on commodity hardware.

Simple API to make training scripts run on any hardware (multi-GPU, TPU, mixed precision) with minimal code changes.

Lightweight, fast Python library for embedding generation with ONNX Runtime. Supports text, sparse (SPLADE), and late-interaction (ColBERT) embeddings without GPU dependencies. Apache 2.0 licensed.

GPU-accelerated feature engineering and preprocessing library for tabular data. Manipulates terabyte-scale datasets to train deep learning recommender systems. Component of NVIDIA Merlin framework. Apache 2.0 licensed.

GPU-accelerated machine learning algorithms with scikit-learn compatible API. 10-50x faster than CPU implementations for large datasets. Apache 2.0 licensed.

GPU-accelerated data loading and augmentation library with highly optimized building blocks for deep learning applications. Apache 2.0 licensed.

Multi-agent reinforcement learning library with JAX-accelerated environments and baselines.

GPU-accelerated robot learning framework.

Kubernetes operator for LLM serving with GPU scheduling and model lifecycle management across vLLM, SGLang, and TensorRT-LLM.

Open-source AI compute and programming platform built around the MAX Engine and Mojo programming language.