Skip to content
View dewitt4's full-sized avatar
:electron:
Building AgentaFlow SRO for optimizing AI/ML
:electron:
Building AgentaFlow SRO for optimizing AI/ML

Block or report dewitt4

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
dewitt4/README.md

Hi there GitHubers 👋

  1. ML Training Clusters - Optimize GPU allocation across multiple training jobs
  2. Kubernetes GPU Workloads - Native Kubernetes scheduling for AI/ML workloads
  3. LLM Inference Services - Reduce costs with intelligent batching and caching
  4. Multi-Model Deployments - Load balance requests across model instances
  5. Cost Optimization - Track and minimize AI infrastructure spending
  6. Performance Debugging - Identify and resolve bottlenecks
  • 🌱 I’m focused on optimizing LLMs and Securing them from Attack
  • 😄 My top skills: being adaptable, scrapy, determined
  • âš¡ Fun fact: By the time the future gets here it will be the present

Pinned Loading

  1. llmguardian llmguardian Public

    Comprehensive LLM AI Model protection | Protect your production GenAI LLM applications | cybersecurity toolset aligned to addressing OWASP vulnerabilities in Large Language Models - https://genai.o…

    Python 4 4

  2. Finoptimize/agentaflow-sro-community Finoptimize/agentaflow-sro-community Public

    Manage AI and Machine Learning workloads more efficiently with lower cost: GPU Orchestration / Scheduling / Routing / Serving / Optimization / Observability for AI/ML systems

    Go 2 3

  3. ai-model-security-monitor ai-model-security-monitor Public

    Security monitoring tool that helps protect AI models from common attacks.

    Python 3 1

  4. ai-security-alerts ai-security-alerts Public

    Security monitoring system that logs suspicious activities and alerts your security team, allowing you to make informed decisions about escalating genuine threats.

    Python 4 1

  5. AgentaFlow/fluxai AgentaFlow/fluxai Public

    FluxAI is a cost optimization and observability platform for AWS Bedrock that helps companies reduce their LLM expenses by 30-50% through intelligent caching, smart routing, and real-time analytics.

    Python 1 1

  6. identity identity Public

    Forked from gorillaether/Identity

    Membership Gate Pro 3 tiers walletconnect plus firebase auth and nft ID

    TypeScript