latency test enhancement - part 1 #128

	name: Unit Test

	on:
	push:
	branches: [ main ]
	paths:
	- "python/sglang/**"
	- "test/**"
	pull_request:
	branches: [ main ]
	paths:
	- "python/sglang/**"
	- "test/**"
	workflow_dispatch:

	concurrency:
	group: unit-test-${{ github.ref }}
	cancel-in-progress: true

	jobs:
	unit-test:
	runs-on: self-hosted

	steps:
	- name: Checkout code
	uses: actions/checkout@v3

	- name: Install dependencies
	run: \|
	source $HOME/venv/bin/activate
	echo "$HOME/venv/bin" >> $GITHUB_PATH

	pip cache purge
	pip install --upgrade pip
	pip install -e "python[all]"
	pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/ --force-reinstall
	pip install --upgrade transformers
	pip install accelerate

	- name: Test Frontend Language with SRT Backend
	run: \|
	cd test/lang
	python3 test_srt_backend.py

	- name: Test OpenAI API Server
	run: \|
	cd test/srt
	python3 test_openai_server.py

	- name: Test Accuracy
	run: \|
	cd test/srt
	python3 test_eval_accuracy.py
	python3 models/test_causal_models.py

	- name: Test Frontend Language with OpenAI Backend
	run: \|
	cd test/lang
	python3 test_openai_backend.py

Provide feedback