kjtaed

Pinned Repositories

FasterTransformer
Transformer related optimization, including BERT, GPT
Language:C++00
FasterTransformer
Transformer related optimization, including BERT, GPT
Language:C++6.1k 61 625901
server
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
Language:Python8.9k 149 3.9k1.5k

kjtaed's Repositories

kjtaed/FasterTransformer
Transformer related optimization, including BERT, GPT
Language:C++00