Benchmark Tune

Use this skill when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing ctx/batch/ubatch/mmap/mlock/speculative-decoding sweeps, running benchmark tune on local or SSH hosts, collecting JSON evidence, and applying tolerance-aware recommendations. Trigger for requests mentioning benchmark tune, tuning tok/s, ctx_size tradeoffs, mmap or mlock tuning, speculative decoding, MTP, ngram, draft models, or replacing old gpu tune usage.

mesh-llm Updated 4k repo stars
Mesh LLM web console

File contents

mesh-llm/mesh-llm commit 155ee59546

Frequently asked questions

npx get-skill add mesh-llm/benchmark-tune