Merge pull request #1 from EvolvingLMMs-Lab/dev/fix_multi_img_ci #4

	name: Accuracy Test

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

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

	jobs:
	accuracy-test:
	if: github.repository == 'sgl-project/sglang' \|\| github.event_name == 'pull_request'
	runs-on: 1-gpu-runner

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

	- name: Install dependencies
	run: \|
	pip install --upgrade pip
	pip install -e "python[all]"
	pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/ --force-reinstall

	git clone https://github.com/merrymercy/human-eval.git
	cd human-eval
	pip install -e .

	- name: Evaluate Accuracy
	timeout-minutes: 20
	run: \|
	cd test/srt
	python3 test_eval_accuracy_large.py

Provide feedback