Profile Picture
  • All
  • Search
  • Images
  • Videos
    • Shorts
  • Maps
  • News
  • More
    • Shopping
    • Flights
    • Travel
  • Notebook
Report an inappropriate content
Please select one of the options below.

Top suggestions for NVIDIA

Tensorrt
Tensorrt
Tensorrt LLM
Tensorrt
LLM
Tensorrt LLM Serve
Tensorrt LLM
Serve
Tensorrt Edge LLM
Tensorrt Edge
LLM
Tensorrt LLM C++
Tensorrt
LLM C++
Tensorrt Bf16
Tensorrt
Bf16
Tensorrt LLM Optimization
Tensorrt LLM
Optimization
NVIDIA Dynamo
NVIDIA
Dynamo
NVIDIA LLM
NVIDIA
LLM
Tensorrt V1.0.0
Tensorrt
V1.0.0
Tensorrt Download
Tensorrt
Download
FPGA LLM Inference
FPGA LLM
Inference
NVIDIA Logo
NVIDIA
Logo
Rife Tensorrt Engine
Rife Tensorrt
Engine
Tensorrt LLM C++ Deploy
Tensorrt LLM
C++ Deploy
Tensorrt LLM Local Agent
Tensorrt LLM
Local Agent
Tensorrt Examples
Tensorrt
Examples
Vultr
Vultr
Nltent315
Nltent315
Tensorflow vs Pytorch
Tensorflow
vs Pytorch
基于 Python 的速度选择器模拟实验视频
基于 Python
的速度选择器模拟实验视频
LLM Power Ghidra
LLM Power
Ghidra
Mujoco 大规模并行训练
Mujoco
大规模并行训练
What Is Deepseek Ai
What Is Deepseek
Ai
TRT LLM
TRT
LLM
NVIDIA Tensorrt
NVIDIA
Tensorrt
LLM Quantization
LLM
Quantization
  • Length
    AllShort (less than 5 minutes)Medium (5-20 minutes)Long (more than 20 minutes)
  • Date
    AllPast 24 hoursPast weekPast monthPast year
  • Resolution
    AllLower than 360p360p or higher480p or higher720p or higher1080p or higher
  • Source
    All
    Dailymotion
    Vimeo
    Metacafe
    Hulu
    VEVO
    Myspace
    MTV
    CBS
    Fox
    CNN
    MSN
  • Price
    AllFreePaid
  • Clear filters
  • SafeSearch:
  • Moderate
    StrictModerate (default)Off
Filter
  1. Tensorrt
  2. Tensorrt LLM
  3. Tensorrt LLM
    Serve
  4. Tensorrt
    Edge LLM
  5. Tensorrt LLM
    C++
  6. Tensorrt
    Bf16
  7. Tensorrt LLM
    Optimization
  8. NVIDIA
    Dynamo
  9. NVIDIA LLM
  10. Tensorrt
    V1.0.0
  11. Tensorrt
    Download
  12. FPGA LLM
    Inference
  13. NVIDIA
    Logo
  14. Rife Tensorrt
    Engine
  15. Tensorrt LLM
    C++ Deploy
  16. Tensorrt LLM
    Local Agent
  17. Tensorrt
    Examples
  18. Vultr
  19. Nltent315
  20. Tensorflow
    vs Pytorch
  21. 基于 Python
    的速度选择器模拟实验视频
  22. LLM
    Power Ghidra
  23. Mujoco
    大规模并行训练
  24. What Is Deepseek
    Ai
  25. TRT
    LLM
  26. NVIDIA Tensorrt
  27. LLM
    Quantization
You now convert any LLM into a faster one without retraining from scratch.NVIDIA just did this to their 30B model. Here's the trick:1. Duplicate the model into two copies2. Freeze one copy, it just reads the prompt and remembers context3. Train the other copy to write chunks of text at once instead of one word at a time4. Run them togetherThe frozen copy barely costs anything (it's already trained). The new copy only needed ~8% of the original training data to learn the new trick.Result: 2.4x fa
0:13
You now convert any LLM into a faster one without retraining from …
103.4K views1 day ago
x.comLior Alexander
See more videos
Static thumbnail place holder
More like this
  • Privacy
  • Terms