Это пробный урок. Оформите подписку, чтобы получить доступ ко всем материалам курса. Премиум

  1. Урок 1. 00:02:01
    Course Intro
  2. Урок 2. 00:01:48
    Usecase
  3. Урок 3. 00:06:43
    How are vectors constructed
  4. Урок 4. 00:03:27
    Choosing the right DB
  5. Урок 5. 00:03:27
    Vector compression
  6. Урок 6. 00:06:59
    Vector Search
  7. Урок 7. 00:05:38
    Milvus DB
  8. Урок 8. 00:00:43
    LLM Intro
  9. Урок 9. 00:08:31
    How LLMs work
  10. Урок 10. 00:03:08
    LLM text generation
  11. Урок 11. 00:05:10
    LLM improvements
  12. Урок 12. 00:05:28
    Attention
  13. Урок 13. 00:03:40
    Transformer Architecture
  14. Урок 14. 00:08:28
    KV Cache
  15. Урок 15. 00:04:38
    Paged Attention
  16. Урок 16. 00:04:01
    Mixture Of Experts
  17. Урок 17. 00:03:40
    Flash Attention
  18. Урок 18. 00:03:33
    Quantization
  19. Урок 19. 00:05:14
    Sparse Attention
  20. Урок 20. 00:05:31
    SLM and Distillation
  21. Урок 21. 00:04:58
    Speculative Decoding
  22. Урок 22. 00:09:44
    Reasoning Models with Human Feedback
  23. Урок 23. 00:04:12
    Chain of Thought
  24. Урок 24. 00:02:57
    Tools used by LLMs
  25. Урок 25. 00:03:14
    Inference Time Scaling and Sunmmary
  26. Урок 26. 00:05:25
    Transformers Masked Attention
  27. Урок 27. 00:04:09
    Multihead Attention 1
  28. Урок 28. 00:11:16
    Context Engineering
  29. Урок 29. 00:10:54
    Agents - Course Video
  30. Урок 30. 00:11:25
    MCP
  31. Урок 31. 01:03:29
    Zoom Class 2025-07-13
  32. Урок 32. 01:23:22
    Zoom Class 2025-08-10