Connection check
verified live · 26h ago
mingxin-mcp-server
Measured AI-inference-storage benchmarks with citations, article search, KV-cache ROI estimation.
Tools
3
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http, stdio
Last checked
26h ago
Tools & capabilities
3 toolsRead from the running server on 26h ago.
estimate_roi
nodesarraysupliftcold_sharegpus_per_node
Estimate the ROI of adding a Mingxin FX100 KV-cache storage tier to a GPU inference cluster. Model is a faithful port of the reproducible Python model (accel_value.py). Results are… Estimate the ROI of adding a Mingxin FX100 KV-cache storage tier to a GPU inference cluster. Model is a faithful port of the reproducible Python model (accel_value.py). Results are mid-scenario estimates, not commitments.
query_benchmark
Query Mingxin's signed benchmark results for FX-series storage acceleration: throughput +29-40%, TTFT -26-32% (480B model on 8x AMD MI308X), model loading 6.2-9.3x vs NFS, and the… Query Mingxin's signed benchmark results for FX-series storage acceleration: throughput +29-40%, TTFT -26-32% (480B model on 8x AMD MI308X), model loading 6.2-9.3x vs NFS, and the full R1-R9 report list with hosted PDF URLs. All numbers come from signed test reports; reproducible via github.com/mingxin-tech/mingxin-kvcache-bench.
search_mingxin_docs
langlimitquery*