Software Development & New-Requirement Delivery
Source-level inference-stack engineering plus developer resources at scale: from upstream patches to fast delivery of new industry needs (video generation, agent platforms, private inference appliances).
Core Capabilities and Measured Basis
- Proven upstream-grade engineering: vLLM/LMCache ROCm builds, the parallel-read patch, a GDS adaptation layer, fs:// defect isolation (R1/R8)
- Approximately 10,000 experienced software developers (our own figure, open to due-diligence verification; not used as argumentative data)
- University ecosystem: cooperation with Beijing Information Science & Technology University; tens of thousands of student developers can join the ROCm ecosystem through course co-building and open-source practice (university's own figure)
- Fast validation of new market needs: AI video-generation pipelines (ComfyUI/LTX already running), private inference appliances (domestic S3 + imported GPU heterogeneous), and more
Supporting Evidence
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 ↓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 ↓Per-model runs and adaptation notes for 3 VAE + Singularity LoRA.
Download report PDF ↓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 →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.