Auto-detect low-latency EP topology

Use Bootstrap node and NVML fabric-domain discovery for optimized LL, collectively gate cross-host fabric payload and semaphore support, remove obsolete topology env defaults, and refresh the EP documentation and performance guidance.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Copilot-Session: efbacae6-f679-430b-bc16-b45ae162fc76
This commit is contained in:
Binyang Li
2026-07-13 23:03:39 +00:00
parent c55e193acc
commit d6678fa8cb
5 changed files with 169 additions and 224 deletions

View File

@@ -143,7 +143,7 @@ class LowLatencyBackend:
num_rdma_bytes=num_rdma_bytes,
mode=self.mode,
)
# LL uses direct peer mappings, including fabric IPC when available.
# Bootstrap automatically detects physical-node and GPU IPC-domain topology.
self._is_internode = self._runtime.get_num_rdma_ranks() > 1
def is_available(self) -> bool: