Q&A: How KRAFTON Built PUBG Ally, a Co-Playable Character Powered by NVIDIA ACE | NVIDIA Technical Blog

This post details the technical architecture of KRAFTON's PUBG Ally, a co-playable character powered by NVIDIA ACE. It highlights the on-device pipeline combining NVIDIA ASR, a 2B-parameter Mistral-NeMo-Minitron-2B SLM, and a custom TTS model. Key engineering efforts focused on minimizing latency through prompt engineering for KV cache optimization and a System 1/System 2 architectural split, where a behavior tree handles fast, reactive gameplay and the SLM handles deliberate reasoning. The post also discusses domain adaptation for PUBG-specific terminology and grounding responses in actual game state by constraining the operational environment (single map, mode, fixed item taxonomy). The quantized SLM's ability to run on GPUs with as little as 8GB VRAM is also noted.
More from the Agentic AI Infrastructure Acceleration with BlueField DPUs trail
- Building Reliable Data Analytics Agents: Lessons from the KDD Cup | NVIDIA Technical Blog
- Validate AI Factory Changes with Digital Twins and AI Agents | NVIDIA Technical Blog
- Scaling Decision Optimization to 100 Million Variables and Beyond with mPDLP in NVIDIA cuOpt | NVIDIA Technical Blog
- Build Applications on NVIDIA BlueField Faster with NVIDIA DOCA Agent Skills | NVIDIA Technical Blog
- Tracing Agent Harness Behavior with NVIDIA NeMo Relay | NVIDIA Technical Blog