Mattias Dürrmeier

mattduerrmeier

·

mattduerrmeier

AI & ML interests

LLM Inference, faster and more efficient kernels, local inference

Recent Activity

upvoted a paper about 10 hours ago

DFlash: Block Diffusion for Flash Speculative Decoding

upvoted a changelog about 14 hours ago

Faster Tensor Viewer

upvoted a paper 1 day ago

UltraBERT: Beyond the Limit of BERT Pre-Training

View all activity

Organizations

New activity in deepseek-ai/DeepSeek-V4-Flash 6 months ago

How to run deepseek on Ada GPUs？Mine is L20.

#25 opened 6 months ago by

Should the "index_topk" be updated to 1024 just like the Pro model?

#23 opened 6 months ago by

Questions on MoE Hash Routing

#22 opened 6 months ago by