import os from chutes.chute import NodeSelector from chutes.chute.template.sglang import build_sglang_chute os.environ["NO_PROXY"] = "localhost,127.0.0.1" chute = build_sglang_chute( username="ryan888", readme="matt0xdev/affine-5CY88hoZChb9NGTvss5LDHddPrmZ4LJb4q2cSESAVoAt1qcX", model_name="matt0xdev/affine-5CY88hoZChb9NGTvss5LDHddPrmZ4LJb4q2cSESAVoAt1qcX", image="chutes/sglang:nightly-2025091100", concurrency=24, revision="8a9ca7839281a9b859a04a4c7c2350718fe89975", node_selector=NodeSelector( gpu_count=8, include=["h100_nvl", "pro_6000", "l40", "a40", "a100", "a100_sxm", "h800", "h100", "a6000_ada", "h20", "l40s", "h200"], ), engine_args=( "--context-length 262144 " "--tool-call-parser qwen25 " "--attention-backend fa3 " "--cuda-graph-max-bs 24 " ), shutdown_after_seconds=1600, )