Ep:3 How To Let Go with Buddhist Monk Ven. Tri Dao
Letting go is a challenging yet essential aspect of our journey towards inner peace. Ven Tri Dao emphasizes that it's not an easy process because our minds tend to hold on to emotions and thoughts, often driven by past experiences and survival instincts. Understanding why we cling to certain though…
#200 CEO & Co-Founder Together AI, Vipul Ved Prakash w/ Bucky Moore: Super Cycle
Guests: Vipul Ved Prakash, CEO and co-founder of Together AI; and Bucky Moore, partner at Kleiner Perkins
No one knows for sure whether the future of AI will be driven more by research labs and AI-native companies, or by enterprises applying the technology to their own data sets. But one thing is f…
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Large Language Models (LLMs) employ auto-regressive decoding that requires sequential computation, with each step reliant on the previous one's output. This creates a bottleneck as each step necessitates moving the full model parameters from High-Bandwidth Memory (HBM) to the accelerator's cache. W…
Interviewing Tri Dao and Michael Poli of Together AI on the future of LLM architectures
This interview is on YouTube and podcast players.
Giving a voice to researchers is the best way to cut through the noise and understand what is happening with core developments of LLM technologies. I’m excited to get to talk with Michael Poli (Stanford PhD student + research at Together AI) and Tri…
Odd Jobs #1: Buddhist Monk
Ajahn Tri Dao is a Buddhist Monk who gave us the time of day and told me all about what it’s like to be a Buddhist Monk and a lot of other stuff!
Arxiv paper - Long-Context State-Space Video World Models
In this episode, we discuss Long-Context State-Space Video World Models by Ryan Po, Yotam Nitzan, Richard Zhang, Berlin Chen, Tri Dao, Eli Shechtman, Gordon Wetzstein, Xun Huang. The paper introduces a novel video diffusion model architecture that uses state-space models (SSMs) to extend temporal m…
Ep 74: Chief Scientist of Together.AI Tri Dao On The End of Nvidia's Dominance, Why Inference Costs Fell & The Next 10X in Speed
Fill out this short listener survey to help us improve the show: https://forms.gle/bbcRiPTRwKoG2tJx8
Tri Dao, Chief Scientist at Together AI and Princeton professor who created Flash Attention and Mamba, discusses how inference optimization has driven costs down 100x since ChatGPT's launch throug…
CÔNG CỤ TÌM KIẾM PODCAST
Bạn có thể sử dụng trang web của chúng tôi để tìm kiếm các podcast3,830,113và các tập196,576,419theo người, địa điểm hoặc chủ đề.
If I have seen further than others, it is by listening to podcasts and standing upon the shoulders of
giants.
‐ Isaac "Llamacorn" Newton
CHỈNH SỬA
Cảm ơn bạn đã giúp cơ sở dữ liệu podcast luôn cập nhật.
