SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Long Video Gen Infrastructure

A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

Pure Rust Inference Engine

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.

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).

GLM-5.2-NVFP4-REAP-469B serving on SM120 (4× RTX PRO 6000 Blackwell) — one-command vLLM launch recipe, 250K context, DeepSeek Sparse Attention + MTP speculative decode

AdaLLM is an NVFP4-first inference runtime for Ada Lovelace (RTX 4090) with FP8 KV cache and custom decode kernels. This repo targets NVFP4 weights and keeps the entire decode path in FP8

记录量化LLM中的总结。

Bleeding-edge ComfyUI for NVIDIA DGX Spark (GB10/Blackwell/sm_121a). CUDA 13 + SageAttention v3 (sm_121a) + NVFP4 + 14 custom-node packs + Flux 2 Dev / LTX 2.3 22B / ACE-Step v1.5 XL Turbo pre-bundled with abliterated text-encoder paths.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

A production-ready Docker setup for ComfyUI that unlocks the full potential of NVIDIA Blackwell GPUs (RTX 50 series) through 4-bit quantization with NVFP4.

From-scratch C++/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a) — the best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents on top of the fastest single-stream decode on the 5090 (beats llama.cpp, at-or-ahead of vLLM on NVFP4). 100% written by Claude Code.

[ACL 2026 Main] Code for the paper "ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs"

llama.cpp fork optimized for NVIDIA DGX Spark / GB10 (Blackwell, SM 12.1) — TurboQuant weights + KV, NVFP4, DFlash MTP

Lynn 原生 LLM 推理引擎 · W4A8/NVFP4 量化 · 自写 CUDA/Triton kernel · MoE · 投机解码 | Lynn-native LLM inference engine for NVIDIA Blackwell

NVFP4 inference on Blackwell GeForce (RTX 5090/5080/5070 Ti/RTX PRO 6000) — SM120 patches for vLLM + FlashInfer + CUTLASS. 175 tok/s on Qwen3.6-35B MoE.

LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)

Run the AEON Bench suite on your own hardware: verified HuggingFace pull → serve → benchmark (text · agentic ×3 harnesses · vision · audio · arena · perf) → ed25519-signed attested submit.