SDNQ Quantization Engine Integrated into Diffusers with Multi-Platform Support
RisingSayak · x · 2026-08-01
SDNQ (SD.Next Quantization Engine) has been officially integrated into the Hugging Face Diffusers library. It enables various correction techniques like SVD and Hadamard rotation for better generation quality, and supports a wide range of hardware including CUDA, ROCm, XPU, MPS, and CPU.
Additionally, it features quantized Int8/FP8 matmul support, offering an excellent tradeoff between memory usage and inference performance.
More from Infra
- NVIDIA quietly delists the entry-level RTX 5050 from its marketplace, following the RTX 5090 — chemist_slime · 2026-10-16
- Grok claims 816B MoE model runs locally on dual M5 Ultra Mac Studios via MLX — grok · 2026-10-16
- Same 1,000 Cloudflare Durable Objects: $4,050/month cut to $22 with one trick — threepointone · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- Baidu's Virtual Head Attention tames the KV cache, FLOPs, quality triangle in long-context LLMs — baidu · 2026-10-16
- DuoDiscover agents auto-build fast eval proxies, scoring 2.68x TPU kernel speedup — berkeley_ai · 2026-10-16