[CI] Migrate tone_tests to CUDA 13: pull cu130 wheel, adapt sglang/vllm paths, add NCCL env & offline model cache#2811

Open

luketong777 wants to merge 10 commits into

mainfrom

ketong/fix_ci_nccl

Commits on Jul 8, 2026

fix(tone_tests): inject NCCL_GIN_TYPE=0 env var into test container
luketong777
committed
fix(ci): select cu130 wheel artifact for integration test to match CUDA 13 image
luketong777
committed
fix(tone_tests): correct sglang test path and create log dir in run-single
luketong777
committed
fix(tone_tests): correctly clean stale wheels in get_whl to avoid installing wrong CUDA wheel
luketong777
committed
fix(tone_tests): fix vllm test OOM (gpu-mem-util 0.85) and correct mooncake proxy path
luketong777
committed
fix(tone_tests): drain GPU memory between cases in run-all to avoid cross-test OOM
luketong777
committed
fix(tone_tests): run vllm test on GPU 6,7 to align with sglang tests
luketong777
committed
feat(tone_tests): use local HF cache offline when model already downloaded
luketong777
committed
fix(tone_tests): force-kill host GPU-holding PIDs in drain to fully clear residual memory
luketong777
committed

Commits on Jul 9, 2026

fix(tone_tests): restart container between run-all cases to reset GPU/ERDMA state (keeps deps)
luketong777
committed