Statements (23)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:Neural_Engine
|
| gptkbp:announced |
2023
|
| gptkbp:architecture |
single-core
|
| gptkbp:competitor |
gptkb:NVIDIA_GPU
gptkb:Google_TPU gptkb:AMD_Instinct |
| gptkbp:designedFor |
AI inference
|
| gptkbp:developedBy |
gptkb:Groq
|
| gptkbp:marketedAs |
alternative to GPU
|
| gptkbp:notableFeature |
energy efficiency
deterministic execution streaming output |
| gptkbp:notableFor |
low latency
high throughput |
| gptkbp:standsFor |
gptkb:Language_Processing_Unit
|
| gptkbp:supports |
LLM inference
real-time AI applications |
| gptkbp:usedFor |
large language models
transformer models |
| gptkbp:usedIn |
gptkb:GroqCloud
|
| gptkbp:bfsParent |
gptkb:Language_modeling
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
Groq LPU
|