AMD
Official@amd
Offers specialized quantization and model optimization capabilities for deploying high-performance transformer architectures on ROCm-enabled hardware and ONNX runtimes.
Agent Skills by AMD
Showing 71 vetted skills indexed across 2 GitHub repositories.
amdagent-hub-release
Cut frozen-binary and npm sidecar releases for GAIA agents via tag-triggered CI pipelines.
amdgithub-issue-response
Drafts protocol-compliant replies to GitHub issues, PR comments, and reviews for amd/gaia.
amdtesting-the-gaia-agent
Test the GAIA agent end-to-end through the Go TUI control API.
amdlemonade-client-patterns
Guides safe modifications to LemonadeClient, its callers, and the GAIA test suite.
amdanalyzing-claude-sessions
Analyze local Claude Code session transcripts to measure usage patterns, failures, and token costs.
amdgaia-build-agent
Scaffold, implement, and test new GAIA agents as Python Agent subclasses with @tool methods.
amdgaia-technical-presentation
Generates technical slide decks from source documents as self-contained printable HTML.
amdgaia-release
Automates the GAIA release workflow from notes drafting through tagging, publishing, and announcement.
amdintegrate-hub-agent
Guides embedding pre-built GAIA hub agents into developer applications via npm or Python.
amdgaia-testing
Runs unit, integration, and real-world hardware test tiers for GAIA with screenshot and trace evidence.
amddriving-the-tui
Drives and validates the GAIA TUI through its loopback control API with screenshots, recordings, and diagnostics.
amdgaia-executive-presentation
Generate executive slide decks from source documents as self-contained printable HTML.
amdweekly-audit-patterns
Documents the invariants of the nightly Claude audit GitHub Actions workflow.
amdporting-agent-to-hub
Ports in-repo GAIA agents into published, installable Agent Hub packages.
amdadding-eval-scorecard
Adopt the per-agent eval scorecard workflow for GAIA hub agents with release gating.
amdsecurity-assessment
Triage reported vulnerabilities and compute CVSS 4.0 scores for PSIRT decisions.
amdintegrate-gaia
Integrate the @amd-gaia/gaia npm package to run or embed GAIA's local agent sidecar.
amdgaia-voice
Defines the GAIA agent's conversational voice, honesty rules, and response delivery standards.
amdintegrate-agent-email
Integrates the @amd-gaia/agent-email npm package into Node, TypeScript, or Electron applications.
amdaction-item-extraction
Extracts owned, dated action items from email threads into two-sided commitment lists.
amdtravel-itinerary
Assembles email booking confirmations into one chronological trip itinerary.
amdinbox-triage
Sorts an email inbox into reply, decision, informational, and noise buckets using scan tools.
amdmeeting-scheduling
Resolves meeting requests in email into accept, decline, or propose-time calendar decisions.
amdnewsletter-digest
Summarize bulk newsletters and promotions into one digest, then archive them.
Frequently Asked Questions About AMD
FAQPage SchemaWhat specific model optimization tasks are supported?▼
These capabilities enable end-to-end post-training quantization for PyTorch and ONNX models. Users can perform model intake analysis, generate hardware-aware quantization plans, execute file-to-file checkpoint compression, and validate final artifacts against metadata and tensor-level accuracy requirements.
Which technical personas benefit from these capabilities?▼
Machine learning engineers and deployment specialists focused on optimizing transformer models for AMD ROCm hardware benefit most. These capabilities assist those managing model drift, verifying environment readiness, and ensuring quantization outputs meet strict deployment contracts.
What are the primary prerequisites for implementation?▼
Implementation requires a configured environment with PyTorch or ONNX Runtime stacks, alongside ROCm drivers for hardware acceleration. Users must validate workspace paths, model references, and system-level dependencies using preflight checks before initiating quantization or evaluation sequences.