initial-d/dsh-plugin-mlquant-benchmark
DeepSeek Harness tools for reproducing the initial-d/ml-quant-trading protocol v1 CPU benchmark: a DSH agent can run the existing benchmark, read the machine-readable artifact, validate it against the benchmark protocol and draft an issue-ready report. The plugin deliberately adds no trading agent, calls no market-data APIs and configures no model provider - it keeps the boundary that benchmark throughput is not trading performance.
dsh-plugin-mlquant-benchmark gives a DeepSeek Harness agent the narrow ability to reproduce the initial-d/ml-quant-trading protocol v1 CPU benchmark end to end: run the existing fixed-protocol benchmark command (seed, panel size, repetitions and thread counts), read the machine-readable JSON artifact, validate that artifact against the benchmark protocol, preserve the evidence bundle and draft an issue-ready report. It deliberately adds no trading agent, calls no market-data APIs and configures no model provider, keeping an explicit boundary that benchmark throughput is not trading performance - the challenge it poses is whether a harness can reproduce a quant benchmark end to end without turning runtime numbers into alpha claims.
Install
dsh plugin --profile web add github:initial-d/dsh-plugin-mlquant-benchmarkCopied verbatim from the README's install block. Installed straight from the repository (no npm package is documented).
Compatibility
A DeepSeek Harness plugin for the ml-quant-trading protocol v1 CPU benchmark; listed on awesome-dsh-plugin (Development & Runtime) via PR #2573. English README.
Details
- Repo: initial-d/dsh-plugin-mlquant-benchmark
- Category: Coding & Development
- Stars: 4
- Version: GitHub repo initial-d/dsh-plugin-mlquant-benchmark (4★); CI badge and an 'Awesome DSH Plugin' badge in the README.
Alternatives
030611/dsh-context-provenance · 030611/qiushi-dsh-evidence-audit · 0x3fffff/dsh-desktop-launcher