Agenten stärken
Installation vom Herausgeber. Kein PlugMCP-Endpunkt.
Host a copy with our keys and logs.
Noch kein paketiertes Release in der Registry. Folgen Sie der README des Repositorys.
Remote-URL oder ein Befehl auf Ihrem Rechner? Worin sich die beiden Installationen unterscheiden
Auf PlugMCP ausführen
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
StartenVom Herausgeber
GPU performance engineering for agents and MCP clients, with an inference-focused skills package and reusable cluster utilities. The project ships 32 task-oriented , a bundled MCP server, safety guards, workload proof schemas, and local validation tools. Together they cover first estimates, benchmark sweeps, kernel profiling, speed-of-light analysis, optimization, and evidence-backed reports.
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
The work comes from GPU fleet performance practice. Every result stays a candidate until the workload, baseline, hardware, precision, parallelism, and engine version are recorded and the result survives a skeptical check.
Claude Code is one supported client, not the project boundary. Client support depends on the surface being installed.
The SKILL.md sources follow the open Agent Skills standard. This repository
maintains and tests the Claude Code and Codex paths. The MCP protocol remains
client-neutral. Configuration helpers for other clients are available, but
they are not part of the release bar.
inference-performance-hints for rough
performance bounds, inference-perf-bench for load sweeps,
inference-tune-sweep for engine knobs, inference-model-eval for quality
gates, and perf-baseline-record with perf-baseline-diff for regressions.inference-workload-profile, inference-kernel-profile for
nsys, inference-kernel-ncu-profile for per-kernel roofline work,
inference-dcgm-correlate, analyze-zymtrace-workload,
inference-graph-diff, and mirage-graph-coverage.inference-model-optimize, inference-quantize-calibrate,
the speculative decode train, tune, and service skills,
inference-decode-step-budget, inference-capacity-sizing, and
inference-known-good-config.inference-perf-tune-report,
inference-perf-synthesize, inference-fleet-leaderboard,
inference-value-ledger, evidence-bundle-init, and the anchored
Prometheus and zymtrace query skills.The documented command-line path remains available when an external observability MCP server is absent.
git clone https://github.com/cfregly/gpu-perf-tune.git
cd gpu-perf-tune
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements/check.txt
make demo
make check
make workload-proof-check
make demo prints the skill and MCP tool surface. A real performance run needs
the bundled server, the target workload, and suitable GPU hardware.
From a clone of this repository:
make install-skills CLIENT=codex
make install-mcp CLIENT=codex
codex mcp get profile_and_optimize
The registration check should report enabled: true. Run
make smoke-mcp-runtime for a live server handshake, then restart Codex after
installation. Codex discovers the linked skills under
~/.agents/skills. Use /skills, invoke a skill with $skill-name, or
describe the task and let Codex select one. The MCP configuration is shared by
Codex CLI, the IDE extension, and the desktop app. See the official Codex
Skills and
MCP references for the client-side
contracts.
claude plugin marketplace add cfregly/gpu-perf-tune
claude plugin install --scope user \
profile-and-optimize@profile-and-optimize-plugins
# Install the bundled MCP server inside the current plugin cache entry.
# Add --full when you need the PDF report dependencies.
bash "$(ls -dt ~/.claude/plugins/cache/profile-and-optimize-plugins/profile-and-optimize/*/server/install.sh | head -1)"
claude mcp get plugin:profile-and-optimize:profile_and_optimize
The health check should report Status: ✔ Connected. Restart Claude Code.
Invoke a skill such as /inference-perf-bench, or describe the task and let
Claude Code select a matching skill. The plugin installs its provenance hook,
but the hook remains inactive until
PROVENANCE_COMMIT_GATE=ask or PROVENANCE_COMMIT_GATE=deny is present in the
Claude hook environment. Install jq on PATH before enabling either mode.
The repository keeps configuration helpers for Cursor, Gemini CLI, and Google Antigravity. They are useful starting points, but changes to those clients do not block a release. The full command list and generic stdio form live in the MCP installation reference.
make install-skills CLIENT=cursor
make install-mcp CLIENT=cursor
Read docs/UPGRADING.md before changing release lines. It
lists the client refresh commands and required installer, AI tuning, MLPerf
rules, and MCP acknowledgement changes.
Every benchmark result, optimization claim, and generated report starts as a candidate. It must be adversarially-confirmed to add value before it ships. The workload is named, the baseline is fair, a skeptic has tried to break the finding, and the receipt maps to lower cost, faster runtime, higher throughput, better reliability, or a clearer operator action.
docs/workload-proof-packet.md defines the
GPU inference packet shape for neocloud buyers and workflow handoffs.
make workload-proof-check validates checked-in packets for completeness and
local handoff metadata.
The skills enforce DRAFT and VERDICT labels, full performance context, asset
validation, and a clear next action. Read
docs/METHODOLOGY.md for the shared rules. The
performance hints adaptation
adds estimate-first triage, with a
synthetic example.
A workflow system can consume workflow_handoff blocks when GPU workload
evidence needs to attach to a broader customer record. ProofPlane is one
possible consumer. It does not change this project's local contract,
validation gates, or runtime dependencies.
plugins/profile-and-optimize/templates/skill/SKILL.md.plugins/profile-and-optimize/server/
and update mcp_surface.py.CONTRIBUTING.md before opening a pull request.make help for the local command reference.The project helps agents measure and report. It does not tune a cluster by itself. Every number depends on the workload and runtime context. Datasheet speed-of-light ceilings are upper bounds, not promises. External systems such as Grafana, Prometheus, GitHub, and zymtrace still need operator credentials and their own client configuration.
Project-authored material is MIT licensed. Third-party adaptations
retain their own terms and attribution in
THIRD_PARTY_NOTICES.md and LICENSES/.
Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Gpu Perf Tune läuft lokal über stdio.
Zuletzt geprüft: 2026-10-28. Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.
