From 7b06a6078677817fef0d90a5e8af88340e73ce39 Mon Sep 17 00:00:00 2001 From: Qinghua Zhou Date: Mon, 11 May 2026 20:59:12 +0000 Subject: [PATCH] test/ext/ep: make HT test Config env-driven Allow tuning the internode HT test cfg from the environment without editing the source. Supported variables (all optional): MSCCLPP_EP_NSM (default 152) num channels / SMs MSCCLPP_EP_NVL_SEND (default 8) MSCCLPP_EP_NVL_RECV (default 256) MSCCLPP_EP_RDMA_SEND (default 16) MSCCLPP_EP_RDMA_RECV (default 128) The defaults match what we use for 16-node GB200 bench runs (e.g. NVL_RECV=512 to satisfy the HT combine assert at 16 nodes). --- test/python/ext/ep/test_internode_multirank.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/python/ext/ep/test_internode_multirank.py b/test/python/ext/ep/test_internode_multirank.py index c7a354e7..c789cc03 100644 --- a/test/python/ext/ep/test_internode_multirank.py +++ b/test/python/ext/ep/test_internode_multirank.py @@ -121,7 +121,7 @@ def main(): # Buffer config for internode HT: needs num_rdma_bytes > 0. Size buffers # using max(hidden, bench_hidden) so the optional bench phase fits. - cfg = ep.Config(20, 8, 256, 16, 128) + cfg = ep.Config(int(os.environ.get("MSCCLPP_EP_NSM","152")), int(os.environ.get("MSCCLPP_EP_NVL_SEND","8")), int(os.environ.get("MSCCLPP_EP_NVL_RECV","256")), int(os.environ.get("MSCCLPP_EP_RDMA_SEND","16")), int(os.environ.get("MSCCLPP_EP_RDMA_RECV","128"))) _bench_on = os.environ.get("MSCCLPP_EP_BENCH", "0") == "1" _buf_hidden = max(hidden, int(os.environ.get("MSCCLPP_EP_BENCH_HIDDEN", "0"))) if _bench_on else hidden num_nvl_bytes = cfg.get_nvl_buffer_size_hint(_buf_hidden * x.element_size(), num_ranks)