4 个仓库
Interfaces for managing hardware-specific memory, queues, and driver interactions.
Distinguishing note: Focuses on unified runtime management across heterogeneous backends.
Explore 4 awesome GitHub repositories matching devops & infrastructure · Device Runtime Managers. Refine with filters or upvote what's useful.
Tinygrad is a deep learning framework and tensor computation engine designed for building and training neural networks. It functions as a hardware abstraction layer that manages device memory, command queues, and kernel dispatching across heterogeneous computing architectures. By utilizing a lazy-evaluation approach, the framework constructs computational graphs that defer execution until data is explicitly required, allowing it to process only the necessary operations for a given result. The project distinguishes itself through a just-in-time compilation layer that transforms abstract comput
Manages device-specific interactions including memory allocation and hardware queue commands through a unified interface.
LMCache is a distributed key-value cache manager and tiering system designed to accelerate large language model inference. It functions as a tiered storage layer that offloads tensors from GPU memory to CPU RAM, local disks, or remote object stores, enabling the reuse of cached prefixes across different inference sessions and serving engines. The system differentiates itself through a disaggregated prefill-decode model, which separates prompt processing from token generation by transferring caches between distributed compute nodes. It utilizes peer-to-peer orchestration to share and retrieve
Allows dynamic adding, removing, and resizing of memory device mappings at runtime via API.
ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,
Pushes shared libraries and sets library paths so the runtime can execute models on a MediaTek device.
umu-launcher is a suite of tools designed to launch Windows game binaries on Linux systems. It serves as a runtime orchestrator and compatibility layer launcher that enables cross-platform software execution. The project manages game compatibility through a fix manager that retrieves and applies specific patches and configurations based on unique store identifiers. It also functions as a data isolation tool, allowing for the specification of custom directory paths to keep game configurations and save data separate from the host system. The system automates the deployment of runtime environme
Handles the automated deployment of required runtime libraries and paths to enable game execution.