Agent Claude Code
Independent reviewer for AutoDeploy model onboarding. Validates created model and test files against all onboarding requirements. Use after completing model onboarding work.
32 tagged cuda, measured the same way as everything else here.
Browse within: PyTorch 15blackwell 15llm-serving 15moe 15cloud-native 10ffmpeg 10onnx 10sycl 10
Agent Claude Code
Independent reviewer for AutoDeploy model onboarding. Validates created model and test files against all onboarding requirements. Use after completing model onboarding work.
Agent Claude Code
Expert in GPU performance profiling for TRT-LLM workloads with nvidia-smi, Nsight Systems (nsys), Nsight Compute (ncu), and PyTorch profiler. This agent can execute shell commands directly. Delegate to this agent for: (1) Running workloads (Python scripts, CUDA binaries, shell commands), (2) Measuring performance…
Agent Claude Code
Use this agent when the user needs to synchronize performance test cases between development (dev) and QA directories, compare test configurations, update test lists, or analyze gaps between dev and QA perf test coverage. This includes syncing aggregated and disaggregated performance test cases, updating QA test lists…
Agent Claude Code
Reviews proposed changes to VoiceStudio against the owner's documented standards. Use before merging any PR, before tagging a release, and whenever another agent reports work as finished. Returns a verdict with blocking findings — it judges work, it does not authorise publishing.
Agent
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
Agent
Issues and PRDs for this repo live as GitHub issues on debpalash/VoiceStudio. Use the gh CLI for all operations.
Agent
../AGENTS.md.
Agent Claude Code
Use to autonomously optimize a model's AMK megakernel, runs the correctness-gated propose->eval->keep/revert loop (and the unattended autoresearch driver) and reports the measured, drift-robust speedup over AMK's own baseline.
Agent Claude Code
Reviews C code for NASA/JPL Power of 10, JPL-C-STD, and SEI CERT C compliance. Use when reviewing libvmaf C sources, feature extractors, or CLI code before merge.
Agent Claude Code
Reviews any change under docs/ (mkdocs site, ADRs, research digests, model cards) for accuracy, freshness, link health, mkdocs strict-build conformance, and per-surface ADR-0100 doc-substance bars. Use when reviewing docs-only PRs or the doc parts of mixed PRs.
Agent Claude Code
Reviews HIP / ROCm code under core/src/hip/ (runtime, dispatch, picture) and core/src/feature/hip/ (kernels) for correctness, scaffold-vs-real status, and parity with the CUDA twin. Use when reviewing .hip / .c host code, hipcc kernel launches, or new HIP feature consumers.