Various fixes to enable my experimental llama.turbine port of llamacp… #9

	name: Test Turbine Models

	on:
	workflow_dispatch:
	pull_request:
	push:
	branches:
	- main

	jobs:
	test-turbine-models:
	strategy:
	matrix:
	version: [3.11]
	os: [nodai-ubuntu-builder-large]

	runs-on: ${{matrix.os}}
	steps:
	- name: "Setting up Python"
	uses: actions/setup-python@75f3110429a8c05be0e1bf360334e4cced2b63fa # v2.3.3
	with:
	python-version: ${{matrix.version}}

	- name: "Checkout Code"
	uses: actions/checkout@v2

	- name: Sync source deps
	run: \|
	python -m pip install --upgrade pip
	# Note: We install in three steps in order to satisfy requirements
	# from non default locations first. Installing the PyTorch CPU
	# wheels saves multiple minutes and a lot of bandwidth on runner setup.
	pip install --index-url https://download.pytorch.org/whl/cpu \
	-r pytorch-cpu-requirements.txt \
	-r torchvision-requirements.txt
	pip install --upgrade -r requirements.txt
	pip install -e .[testing]
	pip install -e python/turbine_models

	- name: Show current free memory
	run: \|
	free -mh

	- name: Run stateless_llama tests
	run: \|
	pytest python/turbine_models/tests/stateless_llama_test.py

	- name: Run sd tests
	run: \|
	pytest python/turbine_models/tests/sd_test.py

Provide feedback