#nvfp4 (9 Repositories)
Ranked open-source repositories tagged with #nvfp4, scored by pull request acceptance likelihood and maintainer engagement velocity.
59.5%
3.4h
9 repositories tagged #nvfp4
NVlabs/Sana
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
Avarok-Cybersecurity/atlas
Pure Rust Inference Engine
intel/auto-round
A simple and effective post training quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的后训练量化工具包
avifenesh/bw24
From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).
jpezzulli/sglang-rtxpro6000
Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.
NVlabs/LongLive
Long Video Gen / World Model / World Action Model (Embodied) Infrastructure
avifenesh/memra
Rust + CUDA inference engine for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. Serves safetensors and GGUF over an OpenAI-compatible API, with per-device tuned defaults and speculative decode gated byte-identical to plain decode. Hosted instance: inference.tiyuvta.ai
hasso5703/dgx-spark-qwen38
Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, 72 tok/s greedy median, 1M context, deterministic boots. Flash-Next 176B on one box. One command, everything pinned, and a local cockpit to drive it.
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash
Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.