NVIDIA Triton inference support

[arnocandel]

https://github.com/triton-inference-server/

• [x] Build Triton Docker image with support for FasterTransformer backend for Fusion etc.
• [x] convert h2oGPT models to format that Triton understands https://github.com/NVIDIA/FasterTransformer/pull/569
• [x] run h2oGPT model inside Triton
• [x] create required APIs
• [ ] test scalability on multi-GPU systems
• [ ] quantize to lower precision, and CPU https://github.com/h2oai/h2ogpt/issues/88
• [ ] https://github.com/NVIDIA/FasterTransformer/pull/575/ same for LLaMa once merged

[arnocandel]

https://github.com/triton-inference-server/fastertransformer_backend/blob/main/docs/gptneox_guide.md https://github.com/triton-inference-server/fastertransformer_backend/tree/main/all_models/gptneox