Quantize ONNX Models with ONNX Runtime
Smaller INT8 ONNX models don't guarantee faster inference—pick dynamic or static quantization based on model type, data, and hardware.
WiseOne AI Blog
Updates, guides, and insights from the WiseOne AI team
Showing
98 posts found for 'models'
Shipped in June: Private Mode, OAuth, GLM 5.2, Media Tools, and More
A complete roundup of what NanoGPT shipped in June 2026, including Private Mode improvements, Sign in with NanoGPT, Batch API expansion, new models, media tools, payment updates, privacy controls, and community projects.
Profiling PyTorch Models: Bottleneck Analysis
Identify where model time is spent—data, compute, memory, or communication—and fix it using torch.utils.bottleneck, torch.profiler, and targeted retests.
The open-weight models worth trying on NanoGPT right now
DeepSeek V4 Flash, GLM 5.2, MiniMax M3, and Nemotron 3 Ultra show why open-weight models now deserve first-round testing for coding, long-context work, agents, and enterprise workflows on NanoGPT.
Compiler Optimizations for AI Models
Compilers yield the biggest AI inference gains—fusion, layout tuning, SIMD, and BF16/INT8 with careful profiling.
Scaling AI Validation Across Data Centers
Unified blueprint to validate models, data, and infrastructure across regions with shared metrics, gates, chaos tests, and ownership.
Real-Time Upscaling: Algorithm Benchmarks
Compare upscaling models by speed vs. quality: latency, PSNR/SSIM/LPIPS, VRAM needs, and TensorRT speedups for 2x–4x.
Nanoodle: share AI workflows powered by your users' NanoGPT balance
Nanoodle lets you share NanoGPT workflows that users can open, sign in to, and run with their own NanoGPT balance.
NanoGPT on the THORChain Podcast
Milan joined the THORChain live stream podcast to talk NanoGPT, crypto payments, privacy, AI access, payment stats, and why decentralized liquidity matters for us.
Sign in with NanoGPT: OAuth PKCE for AI Apps
Developers can now add Sign in with NanoGPT to local apps, agents, chat frontends, and OpenAI-compatible clients.