Mingxin

Storage Acceleration (KV Cache Tiering)

FX series all-flash NVMe-oF arrays plus a KV-cache tiering software stack: signed benchmarks on a 480B model in production deployment form show throughput +29–40% and TTFT −26–32%.

Core Capabilities and Measured Basis

Supporting Evidence

R1FX100 Comprehensive LLM Inference & Training Benchmark (8× AMD MI308X)2026-07-03

LMCache parallel-read patch, multi-GPU KV tiering scale-out, concurrent model loading, model-switch effective TPS, training checkpoint concurrent writes (Qwen2.5-32B/7B).

Download report PDF ↓
R2FX100 KV-Cache Benchmark (480B, TP8 long-context, signed)2026-07-05

Qwen3-Coder-480B-FP8, single 8-GPU instance (TP=8 standard production topology), long-context cold recovery, three-way comparison across concurrency levels.

Download report PDF ↓
R3FX100 KV-Cache Benchmark Summary (480B, TP4×2, all metrics, signed)2026-07-06

Dual 4-GPU instances, nine load levels, full metrics (TTFT p50/p90/p99, TPOT, throughput, disk bandwidth); fs:// shared-pool cross-instance hot sharing verified; two independent runs within 5% deviation.

Download report PDF ↓
R4FX100 KV-Cache Benchmark (480B, multi-instance, official, No.-006)2026-07-06

Official compilation of R2 + R3 issued by a third-party testing organization.

Download report PDF ↓
R9Mingxin FX100-HBMM vs NFS Baseline on Huawei Ascend 910B2026-05-30

Huawei Atlas 910B ×8 (Kunpeng-920): model-serving load (DeepSeek-32B/70B), training weight/checkpoint I/O (Qwen-7B), training-data acceleration (YOLOv8/COCO) — three groups against an NFS baseline (Ascend platform, labeled as such; contact us for access).

Contact us for access →

The Engagement Path

Joint test first, decisions second: gate-based acceptance with built-in stop-loss. The full costing model is provided as reproducible Python after NDA — customers can rerun it with their own parameters. Every key figure on this site carries a report ID and is open to third-party verification.