c
contib5

Sarthak S

@contib5

ML Engineer, model compression and FPGA inference

Singapore
Inglese
Alcune informazioni sono riportate in lingua inglese.
Chi sono
I build fast, efficient deep learning systems. I quantize and compress PyTorch models, turn neural networks into FPGA designs with Vivado, and run and debug large GPU training jobs. I can speed up your model, shrink it for edge devices, or get it running on hardware, with clear reports and reproducible code.... Continua a leggere

Competenze

c
contib5
Sarthak S
offline • 

Consulta i miei servizi

Implementazione e distribuzione dell'IA
I will quantize and compress your pytorch model for faster inference
Siti web personalizzati
I will build a fast, responsive website or landing page