awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetServeur MCPÀ proposNotre méthodologiePresse
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

10 dépôts

Awesome GitHub RepositoriesGPU Performance Profilers

Utilities for tracking GPU memory and throughput during model inference.

Explore 10 awesome GitHub repositories matching testing & quality assurance · GPU Performance Profilers. Refine with filters or upvote what's useful.

Awesome GPU Performance Profilers GitHub Repositories

Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
  • deepfakes/faceswapAvatar de deepfakes

    deepfakes/faceswap

    55,289Voir sur GitHub↗

    Faceswap is a comprehensive framework for automated media manipulation and neural face synthesis. It provides a modular pipeline that manages the entire lifecycle of facial feature extraction, deep learning model training, and image conversion. By coordinating complex computer vision workflows, the system enables users to map facial identities between source and destination datasets while maintaining structural alignment and lighting consistency across video frames. The project distinguishes itself through a highly extensible plugin-based architecture that handles hardware-accelerated process

    Benchmarks graphics hardware by tracking memory usage and throughput across varying batch sizes to refine pipeline performance.

    Pythondeep-face-swapdeep-learningdeep-neural-networks
    Voir sur GitHub↗55,289
  • syllo/nvtopAvatar de Syllo

    Syllo/nvtop

    10,150Voir sur GitHub↗

    nvtop est un tableau de bord basé sur le terminal utilisé pour surveiller les performances, l'utilisation de la mémoire et la température de plusieurs processeurs graphiques et accélérateurs matériels. Il fonctionne comme un outil d'administration centralisé pour suivre la santé et la charge de calcul de plusieurs appareils sur un seul système. L'outil se distingue en corrélant les ID de processus système avec la consommation de ressources matérielles, permettant aux utilisateurs d'identifier les applications spécifiques consommant des ressources GPU. Il utilise une couche d'abstraction agnostique du fournisseur pour prendre en charge le matériel de plusieurs fabricants différents au sein d'une seule interface. Le logiciel fournit des métriques de performance en temps réel et une attribution des ressources par processus en utilisant une interface textuelle. Les utilisateurs peuvent gérer les mises en page de l'interface et enregistrer les préférences d'affichage via un fichier de configuration local pour maintenir les paramètres entre les sessions.

    Analyzes individual process resource consumption on GPUs to identify bottlenecks and memory leaks.

    Cadrenoamdapple
    Voir sur GitHub↗10,150
  • dusty-nv/jetson-inferenceAvatar de dusty-nv

    dusty-nv/jetson-inference

    8,734Voir sur GitHub↗

    jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

    Analyzes and debugs GPU-accelerated workloads to optimize AI, graphics, and compute performance.

    C++caffecomputer-visiondeep-learning
    Voir sur GitHub↗8,734
  • tingsongyu/pytorch_tutorialAvatar de TingsongYu

    TingsongYu/PyTorch_Tutorial

    8,018Voir sur GitHub↗

    This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

    Tracks CPU and GPU utilization and data throughput to identify system-level application bottlenecks.

    Python
    Voir sur GitHub↗8,018
  • xuehaipan/nvitopAvatar de XuehaiPan

    XuehaiPan/nvitop

    6,577Voir sur GitHub↗

    Lists running GPU processes with PID, user, and memory, and allows termination from the interface.

    Pythoncommand-line-toolconsolecuda
    Voir sur GitHub↗6,577
  • nvidia/isaac-gr00tAvatar de NVIDIA

    NVIDIA/Isaac-GR00T

    6,222Voir sur GitHub↗

    Measures GPU throughput, utilization, cache hit rates, and memory throughput to identify optimization opportunities.

    Jupyter Notebook
    Voir sur GitHub↗6,222
  • mandiant/capaAvatar de mandiant

    mandiant/capa

    6,062Voir sur GitHub↗

    capa is a binary capability scanner that identifies high-level behaviors and actions an executable can perform, such as network communication or file manipulation. It functions as a malware behavior analysis tool and a MITRE ATT&CK mapping framework, scanning PE, ELF, .NET, and shellcode files through both static analysis and dynamic sandbox report processing. The tool distinguishes itself through a YAML-based detection rule engine that defines detection logic in human-readable files, with conditions expressed as feature combinations and logical operators. It integrates with IDA Pro, Ghidra,

    Limits analysis to specific processes by PID when processing dynamic sandbox reports.

    Python
    Voir sur GitHub↗6,062
  • btraceio/btraceAvatar de btraceio

    btraceio/btrace

    5,989Voir sur GitHub↗

    btrace est un outil de traçage dynamique et un profileur de performance JVM utilisé pour injecter des scripts d'instrumentation sécurisés dans une machine virtuelle Java en cours d'exécution sans nécessiter de redémarrage du processus. Il fonctionne comme un framework d'agent Java et un serveur de protocole de contexte de modèle (Model Context Protocol), exposant les opérations de diagnostic JVM et les outils de traçage aux grands modèles de langage et aux assistants IA. Le projet se distingue en permettant l'injection de code en temps réel et l'instrumentation au niveau du bytecode via un protocole binaire sécurisé. Il garantit la stabilité en production grâce à un moteur d'analyse de sécurité statique qui bloque les modèles de code instables, tels que les boucles et les allocations, pendant la phase de compilation du script. Le système couvre un large éventail de capacités d'observabilité, notamment le traçage de l'exécution des méthodes, le suivi de l'allocation d'objets et la surveillance de l'accès aux champs. Il fournit un profilage des performances via des métriques de latence et l'échantillonnage des données d'exécution, et peut émettre des événements Java Flight Recorder personnalisés pour une analyse native. L'agent prend en charge des stratégies de déploiement flexibles, notamment le démarrage au lancement ou l'attachement à des processus en direct dans des environnements conteneurisés à l'aide de bundles fat JAR.

    Includes utilities for tracking GPU memory and throughput during deep learning model inference.

    Javabtracejavajava-application
    Voir sur GitHub↗5,989
  • google/perfettoAvatar de google

    google/perfetto

    5,558Voir sur GitHub↗

    Perfetto is a platform for system-level performance tracing and analysis on Linux and Android. It combines a high-throughput trace recorder, a SQL-based query engine, and a browser-based visualizer into a single toolchain. The platform covers CPU scheduling and call-stack profiling, native and Java heap memory allocation tracking, GPU and graphics events, and system-wide counters such as CPU frequency and power consumption. The architecture decouples trace recording from offline analysis, using a compact protobuf format for event encoding and columnar storage for efficient SQL queries. The we

    Organizes GPU traces into timelines by device and process, displaying per-kernel metric tables and details.

    C++
    Voir sur GitHub↗5,558
  • regl-project/reglAvatar de regl-project

    regl-project/regl

    5,528Voir sur GitHub↗

    regl is a declarative WebGL library that manages graphics state and GPU resources through functional commands instead of manual binding and state tracking. It provides a command-based drawing abstraction where shaders, attributes, and render state are encapsulated into reusable, compiled functions that can be executed efficiently. What sets regl apart is its scoped state inheritance system, which allows nested drawing commands to inherit and override render state from parent scopes for organized rendering. The library automatically recovers from GPU context loss by restoring buffer and textur

    Regl collects CPU and GPU timing data and draw call counts per command for rendering performance diagnostics.

    JavaScriptjavascriptreglwebgl
    Voir sur GitHub↗5,528
  1. Home
  2. Testing & Quality Assurance
  3. Performance Testing and Analysis
  4. Performance Profiling
  5. GPU Performance Profilers

Explorer les sous-tags

  • Draw Call ProfilersTracks draw call counts, GPU memory allocation, and CPU/GPU execution time per command. **Distinct from GPU Performance Profilers:** Distinct from GPU Performance Profilers: focuses on per-command draw call and timing metrics, not general GPU throughput or model inference profiling.
  • GPU Hardware Metric Visualizers1 sous-tagTranslates cryptic GPU hardware values into actionable information, hierarchically ordered down to individual source lines. **Distinct from GPU Performance Profilers:** Distinct from GPU Performance Profilers: focuses on visualizing and translating hardware metrics into actionable information, not just tracking memory and throughput.
  • GPU Process Analysis6 sous-tagsAnalysis of individual process resource consumption on GPUs to identify bottlenecks and leaks. **Distinct from GPU Performance Profilers:** Distinct from GPU Performance Profilers: focuses on process-level attribution and identification rather than kernel-level throughput analysis.
  • Unified CPU-GPU Performance AnalyzersTools that visualize CPU and GPU algorithm performance to identify optimization opportunities across the system. **Distinct from GPU Performance Profilers:** Distinct from GPU Performance Profilers: focuses on unified CPU and GPU algorithm performance analysis, not just tracking GPU memory and throughput.