2. Build neural network inference library - QueensGambit/CrazyAra GitHub Wiki

At the time of writing there are three back-ends available to run the neural network inference with:

Back-end	GPU Support	CPU Support	Inference Speed	Effort to install
TensorRT (default)	:heavy_check_mark:	:x:	:fire::fire::fire::fire:	:warning::warning:
OpenVino	(:heavy_check_mark:) not tested yet	:heavy_check_mark:	:fire::fire::fire:	:warning:
MXNet	:heavy_check_mark:	:heavy_check_mark:	:fire::fire:	:warning::warning::warning: (CPU only) / :warning::warning::warning::warning: (GPU)
Torch	:heavy_check_mark:	:heavy_check_mark:	:fire:	:warning:

---

Next part:

• 3. Build CrazyAra binary