refactor: Refactor nitro with `cortext.tensorrtllm` engine #10

	name: CI

	on:
	pull_request:
	types: [opened, synchronize, reopened]
	workflow_dispatch:

	jobs:
	build-and-test:
	runs-on: ${{ matrix.runs-on }}
	timeout-minutes: 40
	strategy:
	matrix:
	include:
	- os: "linux"
	name: "amd64-cuda-12-0"
	runs-on: "ubuntu-18-04-cuda-12-0"
	# runs-on: "ubuntu-18-04"
	# - os: "linux"
	# name: "amd64"
	# runs-on: "ubuntu-latest"
	# - os: "windows"
	# name: "amd64"
	# runs-on: "windows-cuda-12-0"
	# - os: "windows"
	# name: "amd64"
	# runs-on: "windows-latest"

	steps:
	- name: Clone
	id: checkout
	uses: actions/checkout@v3

	- name: Install make on Windows
	if: runner.os == 'windows'
	run: \|
	choco install make -y

	- name: Install dependencies
	run: \|
	sudo apt-get install uuid-dev
	ldd --version
	cd cpp/tensorrt_llm/cortex.tensorrt-llm
	make install-dependencies

	# - name: Build engine
	# run: \|
	# cd cpp/tensorrt_llm/cortex.tensorrt-llm
	# make build-engine

	- name: Build example server
	run: \|
	cd cpp/tensorrt_llm/cortex.tensorrt-llm
	make build-example-server

	- name: Download engine
	run: \|
	cd cpp/tensorrt_llm/cortex.tensorrt-llm/examples/server/build
	wget https://huggingface.co/HHrecode/tllm_checkpoint_1gpu_fp8_hermes_engine/resolve/main/engines.tar.gz
	tar -zxvf engines.tar.gz
	export LD_LIBRARY_PATH=$(pwd)/engines/cortex.tensorrtllm

	- name: Run e2e test
	run: \|
	cd cpp/tensorrt_llm/cortex.tensorrt-llm
	make run-e2e-test

	# - name: Package
	# run: \|
	# make package

	# - name: Upload Artifact
	# uses: actions/upload-artifact@v2
	# with:
	# name: cortex.tensorrt-llm-${{ matrix.os }}-${{ matrix.name }}
	# path: ./cortex.tensorrt-llm.tar.gz

Provide feedback