AWS Trainium2
Up to 4x faster training and 3x the memory of first-generation Trainium.
Silicon from Amazon
5 chips on record, newest first.
-
2024
AWS Trainium3
3nm Third-generation AWS training chip, AWS's first on 3nm
up to 362 FP8 PFLOPs per 144-chip Trn3 UltraServer
Absolute -
2023
AWS Trainium2
Not stated by AWS Second-generation AWS training chip
up to 1.3 petaflops of dense FP8 compute per chip
Absolute -
2022
AWS Inferentia2
Not stated by AWS Second-generation inference chip, 32 GB HBM
up to 190 tera floating operations per second (TFLOPS) of FP16 performance per chip
Absolute -
2020
AWS Trainium
Not stated by AWS First-generation AWS training chip, 32 GB per chip
up to 3 petaflops of FP16/BF16 compute power per 16-chip Trn1 instance
Absolute -
2018
AWS Inferentia
Not stated by AWS First-generation AWS machine-learning inference chip, 8 GB DDR4
128 teraOPS on 8-bit integer (INT8) data per chip
Absolute