hopbui
@hopbui3ML Engineer @ Renesas (づ◔ ͜ʖ◔)づ (づ◔ ͜ʖ◔)づ(づ◔ ͜ʖ◔)づ Interested in Vision-Language Model, Robotics, CUDA programming
Checkout our newest CUDA tutorial. research.colfax-intl.com/cutlass-tutori… The topic is software pipelining: overlap mem copying with compute to hide latency. We present the concept in the context of GEMM (matmul), but it's applicable everywhere. e.g., Flash Attention 2 and 3. Conceptually…
Sunday Random Learning - Practice Leetcode - AC 300+ Leetcode problems -Some funny moments youtube.com/clip/UgkxuxQXT… via @YouTube
I just subscribed to ByteByteGo System Design blog.bytebytego.com/?utm_medium=we…
📢 Register now! 📅 #GoogleCloudNext ’21 is coming, October 12-14, 2021. cloud.withgoogle.com/next/register?…
Primer: Searching for Efficient Transformers for Language Modeling arxiv.org/abs/2109.08668 We use evolution to design a new Transformer variant, called Primer. Primer has a better scaling law, and is 3X to 4X faster for training than Transformer for language modeling.
Want to make your inference code in PyTorch run faster? Here’s a quick thread on doing exactly that. 1. Replace torch.no_grad() with the ✨torch.inference_mode()✨ context manager.
🐙 MLOps Basics 🐙 This is really cool! It includes a set of hands-on guides to understand the basics of MLOps. From building the machine learning model to deploying it. It looks very useful to learn about the technology stack for ML engineering. github.com/graviraja/MLOp…
I am very excited to announce we (w/ @ChetanyaRastogi, @advaypal, @chrmanning) will be organizing the first Transformers-only seminar: CS25 Transformers United! at @Stanford focusing on the latest breakthroughs with Transformers in diverse fields: cs25.stanford.edu (1/N)
We wrote up some of the best practices we feel are useful for ML projects github.com/labmlai/labml/… Here's a summary 🧵👇
I solved the @OpenAI Codex Challenge in 133 minutes and 45 seconds, with 4 assists from Codex. ⚡️ challenge.openai.com/codex/results/…
I'm looking for open-source libraries that are particularly useful for EDA & Vizualization of NLP / Textual data. Any suggestions will be highly appreciated! TIA 🙏
United States Trends
- 1. #PaulTyson 187 B posts
- 2. Ramos 58,2 B posts
- 3. #NetflixFight 8.303 posts
- 4. #SmackDown 57,5 B posts
- 5. Jerry Jones 2.541 posts
- 6. Rosie Perez 4.549 posts
- 7. My Netflix 16,9 B posts
- 8. Goyat 20,8 B posts
- 9. Cedric 9.329 posts
- 10. #netfix 1.700 posts
- 11. Nunes 30 B posts
- 12. Buffering 18 B posts
- 13. #BlueBloods 2.504 posts
- 14. Holyfield 6.938 posts
- 15. Michael Irvin N/A
- 16. Naomi 24 B posts
- 17. Bronson 7.057 posts
- 18. Grok 49,4 B posts
- 19. Shinsuke 3.469 posts
- 20. Seth 22,8 B posts
Something went wrong.
Something went wrong.