Popular repositories Loading

1. qwen38-flash-next-2x3090 qwen38-flash-next-2x3090 Public

   Qwen3.8-Flash-Next on 2× RTX 3090 + 128 GB RAM. 2,752 tok/s prefill · 104.5 tok/s decode (131K prompt); full 256K window at 2,654 tok/s prefill and up to 103 tok/s decode.

   Python 82 9

2. foobar_v2 foobar_v2 Public

   Extension of the FooBaR attack on deep neural networks

   Python 1

3. foobar_resnet foobar_resnet Public

   Implementation of FooBaR attack for ResNet architecture

   Python