Mingxin

Domestic GPU Enablement & Joint Optimization

Source-level inference-stack adaptation and measured validation across AMD MI308X, Huawei Ascend 910B, MetaX N260 and other platforms — turning domestic / non-NVIDIA accelerators into production capacity.

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 ↓
R5FX100 KV-Cache Benchmark (14B, HBM efficiency, official, No.-004)2026-07-03

Seven-way comparison (GDS direct read / two re-compute HBM tiers / low-HBM direct read); three-step HBM-equivalence argument. Platform: MetaX N260 single GPU — methodology portable across platforms, numbers not mixed with MI308X.

Download report PDF ↓
R6ComfyUI + LTX-Video 2.3 Full Deployment & Adaptation Report (V2)2026-07-07

All 7 delivered models (3 VAE / fp8 text encoder / text projection / 2 LoRA) running end-to-end on MI308X / ROCm 7.2 with no dtype, operator, or kernel errors.

Download report PDF ↓
R7ComfyUI + LTX-Video 2.3 Model Adaptation Report (AMD MI308X)2026-07-07

Per-model runs and adaptation notes for 3 VAE + Singularity LoRA.

Download report PDF ↓
R8FX100 KV-Cache AMD Code Export + Raw Benchmark Data2026-07

LMCache parallel-read patch (git patch + full before/after), load clients, orchestration and forensic scripts, raw data — enables full third-party reproduction (contact us for access).

Contact us for access →
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.