[๐๐ป๐๐ฒ๐ฟ๐ป ๐๐ถ๐ฟ๐ถ๐ป๐ด]We are hiring a [๐๐ฉ๐ซ๐ข๐ง๐ ๐๐๐๐] [๐๐ฎ๐ฅ๐ฅ-๐ญ๐ข๐ฆ๐] intern working on ๐ฃ๐ฟ๐ถ๐๐ฎ๐๐ฒ ๐๐๐ผ๐น๐๐๐ถ๐ผ๐ป. If you are interested, please apply here https://t.co/FV2RwSri5B and send me an email: zinanlin at microsoft dot com
๐ Image AR models (๐ฉ๐๐ฅ & ๐๐น๐ฎ๐บ๐ฎ๐๐ฒ๐ป) can be distilled to ๐ข๐ก๐ step (up to ๐ฎ๐ญ๐ด๐ ๐ณ๐ฎ๐๐๐ฒ๐ฟ) for the first time!
See ๐ซ๐๐๐๐๐๐๐๐ ๐ซ๐๐๐๐ ๐๐๐ โ
๐ช๐ฒ๐ฏ๐๐ถ๐๐ฒ: https://t.co/m7AXsThqIr
๐ฃ๐ฎ๐ฝ๐ฒ๐ฟ: https://t.co/zzleBDdB3n
https://t.co/o2Fwk2l0Ze
(1/n)
DiTFastAttn
Attention Compression for Diffusion Transformer Models
Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to self-attention's quadratic complexity. We propose DiTFastAttn, a novel post-training compression
Thank @_akhaliq for featuring Skeleton-of-Thoughts! Check out the recorded demo: https://t.co/1vfFgaEoL4
It is just a start--more work to do towards a usable tool. But we genuinely believe in the potential of this data-driven direction to make LLMs more efficient and powerful!
Thank @omarsar0 for featuring Skeleton-of-Thoughts! Check out the recorded demo: https://t.co/1vfFgaEoL4
It is just a start--more work to do towards a usable tool. But we genuinely believe in the potential of this data-driven direction to make LLMs more efficient and powerful!
#ICML Accelerate ๐๐ญ๐๐๐ฅ๐ ๐๐ข๐๐๐ฎ๐ฌ๐ข๐จ๐ง by ๐๐ฑ through a new perspective!
Visit poster #102 on Thursday, July 27th, at 10:30 am.
[๐๐๐ฉ๐๐ซ] OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
https://t.co/21dYN19kpE
(1/3)