blackwell
Qwen3.6-27B-PrismaSCOUT-Blackwell-NVFP4-BF16-vllmQwen3.8-27B-ColdFusion-GAIN-Blackwell-DFlash2-Ultra-V1.0Signal-3.8-27B-NVFP4-Blackwell-DFlash2-Ultra-V1.0gemma-4-31B-it-qat-NVFP4-Blackwellgemma-4-31B-it-qat-NVFP4-mse-BlackwellQwopus3.6-35B-A3B-v1-PrismaSCOUT-Blackwell-NVFP4-BF16-vllm-4.75bitsomnicoder_local9b_blackwell_coregen_hdlfix_v2_hf_r64_epoch1-ggufQwen3-8B-NVFP4-Blackwell
diffusers-blackwell-quantsOutput artifacts for https://github.com/sayakpaul/diffusers-blackwell-quants
zerogpu-blackwell-wheels
ZeroGPU Blackwell (sm_120) wheels
CUDA-extension wheels built for Blackwell (sm_120). PyPI doesn't currently publish sm_120 wheels for most of these libs, and ZeroGPU Spaces can't compile at boot, so Spaces should pin URLs from this dataset directly in requirements.txt.
Usage
URL template:
https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels/resolve/main/wheels/<TAG>/<wheel-filename>
Example, for a Space on torch 2.12 / cu130 / py3.13 that needs… See the full description on the dataset page: https://huggingface.co/datasets/multimodalart/zerogpu-blackwell-wheels.blackwell-ita-artifactsvla-framework-repro-blackwell-20260707
vla_framework — Blackwell 复现结果 (2026-07-07)
vla_framework(develop) 在 RTX PRO 4000 Blackwell ×2 (sm_120, driver 595) 上从零复现的评测结果与视频。
conda env vla_framework,torch 2.11.0+cu128。详见仓库 docs/REPRODUCTION_REPORT_2026-07-07.md。
1. SmolVLA 纯 VLA 基线 — place_bread_skillet
模型 arrow-hf/smolvla-robotwin-place-bread-skillet-50ep-multi,passthrough(无 MPC),robotwin_gt,chunk_exec=50,max_steps=600,subprocess-per-episode。
**env_success 4/10 (40%)**,对照文档 vtc benchmark multi 45% ——… See the full description on the dataset page: https://huggingface.co/datasets/arrow-hf/vla-framework-repro-blackwell-20260707.ubuntu22.04-rtx50series-blackwell-iso
Ubuntu 22.04 LTS 定制镜像 (专为 NVIDIA RTX 50 系列显卡优化)
📋 项目背景 (Project Background)
目前(2026年初),NVIDIA RTX 50 系列(Blackwell 架构,如 RTX 5080 / 5090)已正式发布。然而,由于硬件架构极新,传统的 Ubuntu 官方安装镜像在这些显卡上存在严重的兼容性问题。
本镜像由Jessy(杰西)制作,集成了最新的 NVIDIA 570 系列生产分支驱动,旨在为具身智能(Embodied AI)及深度学习开发者提供“开箱即用”的底层环境。
📋 为什么需要这个镜像?
如果你正在为新配的 RTX 50 系列(5080/5090 等) 工作站安装 Ubuntu 22.04,大概率会遇到死活进不去安装界面的情况。
🚫 传统的“救命药方”失效了
通常遇到显卡不兼容导致的黑屏,网上的常规解法是:
在 GRUB 界面开启 nomodeset(通用驱动模式)。
但实测证明: 对于架构大改的 RTX 50 系显卡,开启 nomodeset… See the full description on the dataset page: https://huggingface.co/datasets/Jessy-Huang/ubuntu22.04-rtx50series-blackwell-iso.blackwell-quantization-results
