Accelerate ROLLCALL A100 Pipeline

Бюджет: $100 - $250 / ⭐ (0)

AI Model Development, Computer Vision, CUDA, Deep Learning, Docker, Neural Networks, Performance Tuning, Python, Pytorch, Software Engineering

I need an experienced PyTorch/CUDA engineer to squeeze every practical second out of our ROLLCALL Wan 2.2 I2V A14B inference pipeline running on an A100 80 GB while keeping the pictures looking exactly the same... (Budget: $100 - $250 USD, Jobs: AI Model Development, Computer Vision, CUDA, Deep Learning, Docker, Neural Networks, Performance Tuning, Python, Pytorch, Software Engineering)

Открыть заказ

AI-черновик отклика

Короткий текст отклика для копирования в оффер: интерес + готовность работать.

Войдите, чтобы сгенерировать AI-черновик.

Войти