Skip to main content
Glama

Arm-Migrate MCP

Migrate your LLM workload to Arm — and prove the speedup with real numbers.

Arm-Migrate is an MCP server plus a GitHub Actions benchmark harness. Connect it to any MCP client (Claude Code, Claude Desktop, …) and ask it to migrate an LLM inference workload to Arm64. It will:

  1. Analyze the workload (analyze_workload) — scans Dockerfiles, compose files, and dependency lists for migration blockers: x86-pinned base images, CUDA-only stacks, missing quantization, arch-specific wheels.

  2. Plan the migration (generate_migration_plan) — emits ready-to-commit artifacts: an arm64 Dockerfile built around llama.cpp with KleidiAI kernels, a CI benchmark workflow, recommended quantization (Q4_0 for KleidiAI's int8mm/dotprod paths), and a migration checklist.

  3. Measure (trigger_benchmark / fetch_benchmark_results) — runs a 3-way benchmark matrix on GitHub's free ubuntu-24.04-arm runners: Arm64 + KleidiAI vs Arm64 baseline vs x86 baseline, using llama-bench with repetitions and captured CPU feature flags.

  4. Report (generate_report) — turns the raw JSON artifacts into a migration report: prompt-processing and token-generation tokens/sec, deltas, hardware context, and a go/no-go recommendation.

Zero-cost, fully reproducible: everything runs on free public-repo CI. No GPUs, no cloud account, no API keys.

Measured results (Neoverse-N2, free GitHub Arm64 runners)

Qwen2.5-0.5B-Instruct, llama-bench, 5 repetitions, 4 threads. Full reports with stddev and hardware context: Q4_0 · Q8_0.

Comparison

Prompt proc.

Generation

Arm optimized kernels vs naive Arm build (Q4_0)

+131%

+44%

KleidiAI vs default kernels (Q4_0)

~0%

~0%

KleidiAI vs default kernels (Q8_0)

+59%

+15%

Arm64+KleidiAI vs x86 runner (Q8_0)

+269%

+155%

The practical guidance that falls out: Q4_0 is fast on Arm out of the box (mainline repack kernels); Q8_0 leaves large gains on the table unless you build with -DGGML_CPU_KLEIDIAI=ON. Arm64 wins token generation — the axis that dominates chat/agent serving cost — across every silicon draw we measured; the x86 prompt-processing picture depends on whether GitHub's mixed pool hands you AVX-512 (see the variance disclosure in the reports).

Related MCP server: ArmBench MCP Server

Why this matters

Arm64 cloud (Graviton, Axion, Cobalt, Ampere) is routinely the cheapest compute per vCPU, and KleidiAI makes CPU-only LLM inference genuinely usable — but teams don't migrate because they can't predict what their workload gains. Arm-Migrate closes that gap: the agent hands you the migration plan and the measured numbers in one conversation.

Quickstart

npm install && npm run build

Register with your MCP client (Claude Code shown):

claude mcp add arm-migrate -- node <path>/dist/index.js

Then ask: "Analyze this Dockerfile for Arm migration and generate a plan."

To reproduce our benchmark numbers: fork, enable Actions, run the arm-bench workflow (workflow_dispatch) — the report lands in the run's artifacts and job summary.

Repository layout

src/            MCP server (TypeScript)
bench/          benchmark scripts + report generator (no deps)
templates/      generated migration artifacts (Dockerfile.arm64, …)
.github/        the arm-bench harness itself

Hackathon

Built for Arm Create: AI Optimization Challenge 2026 (Track 2 — Cloud AI). See RULES.md for the rules digest and DEVLOG.md for an honest build log.

License

MIT

Available Tools

4 tools
analyze_workloadA

Analyze an LLM workload (Dockerfile, compose file, dependency list, or plain description) for Arm64 migration blockers and optimization opportunities. Returns severity-ranked signals with concrete fixes.

Inputs: compose, packages, dockerfile, description.

fetch_benchmark_resultsA

Download artifacts from the latest (or a specific) completed arm-bench run and return the migration report with measured tokens/sec deltas.

Inputs: repo (required), run_id.

generate_migration_planB

Generate ready-to-commit Arm64 migration artifacts: an arm64 Dockerfile (llama.cpp + KleidiAI), a CI benchmark workflow for free GitHub Arm64 runners, build flags, and a migration checklist.

Inputs: quant, model_hint, workload_kind.

trigger_benchmarkA

Trigger the arm-bench workflow (Arm64+KleidiAI vs Arm64 vs x86 benchmark matrix) on a GitHub repo via workflow_dispatch. Requires an authenticated gh CLI; falls back to manual instructions.

Inputs: repo (required), model_url.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: analyze workloads, fetch results, generate migration plans, and trigger benchmarks. No overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (analyze_workload, fetch_benchmark_results, generate_migration_plan, trigger_benchmark).

    Tool Count5/5

    With 4 tools, the set covers the core migration workflow without being over- or under-scoped. Each tool earns its place.

    Completeness5/5

    The tool surface covers the full migration lifecycle: analyze current workload, benchmark performance, generate migration plan, and trigger benchmarks. No obvious gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      A
      maintenance
      Provides AI assistants with tools for Arm architecture development, migration, and optimization, including knowledge base search, code migration analysis, container inspection, assembly performance analysis, and workload performance testing.
      95
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      Helps AI assistants optimize Linux workloads on Arm64 by parsing perf report output, recommending NEON SIMD intrinsics for hot loops, and auditing Python dependency manifests for arm64 wheel availability — all offline and structured.
      4
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Vendor-neutral local LLM inference benchmark and hardware-config advisor for mlx and llama.cpp. Exposes an MCP tool that measures real tokens/second on your own hardware.
      11 npm
      Apache 2.0