deepseek-ai/DeepSeek-R1-Zero
Text Generation
•
Updated
•
6.7k
•
897
darkz baron
darkzbaron
AI & ML interests
nlp and cv and ai
Recent Activity
liked
a model
about 17 hours ago
deepseek-ai/DeepSeek-R1-Zero
liked
a Space
about 18 hours ago
yeliudev/VideoMind-2B
upvoted
a
collection
2 days ago
Orpheus Multilingual Research Release
Organizations
None yet
darkzbaron's activity
liked
a
model
about 17 hours ago
liked
a
Space
about 18 hours ago
upvoted
a
collection
2 days ago
liked
a
model
2 days ago
liked
a
Space
3 days ago
liked
a
model
3 days ago
reacted to
odellus's
post with 👍
3 days ago
liked
a
Space
4 days ago
liked
a
model
5 days ago
liked
a
Space
6 days ago
reacted to
onekq's
post with 🚀
6 days ago
Post
2548
We desperately need GPU for model inference. CPU can't replace GPU.
I will start with the basics. GPU is designed to serve predictable workloads with many parallel units (pixels, tensors, tokens). So a GPU allocates as much transistor budget as possible to build thousands of compute units (Cuda cores in NVidia or execution units in Apple Silicon), each capable of running a thread.
But CPU is designed to handle all kinds of workloads. CPU cores are much larger (hence a lot fewer) with branch prediction and other complex things. In addition, more and more transistors are allocated to build larger cache (~50% now) to house the unpredictable, devouring the compute budget.
Generalists can't beat specialists.
I will start with the basics. GPU is designed to serve predictable workloads with many parallel units (pixels, tensors, tokens). So a GPU allocates as much transistor budget as possible to build thousands of compute units (Cuda cores in NVidia or execution units in Apple Silicon), each capable of running a thread.
But CPU is designed to handle all kinds of workloads. CPU cores are much larger (hence a lot fewer) with branch prediction and other complex things. In addition, more and more transistors are allocated to build larger cache (~50% now) to house the unpredictable, devouring the compute budget.
Generalists can't beat specialists.
- 4 replies
upvoted
a
paper
8 days ago
liked
2
Spaces
8 days ago
liked
a
model
9 days ago
liked
2
Spaces
9 days ago
liked
a
Space
11 days ago
liked
a
model
13 days ago
liked
a
Space
15 days ago