A3 / LAYOUT
当前版本待验证2nodes
DeepSeek-V4-Pro-w4a8-mtp, 2x A3, TP=16 x DP=2. Already aligned with the v0.21.0rc1 Pro 2-node reference (mtp/enforce_eager). Deliberate deviation from upstream: uses --data-parallel-rank (not --data-parallel-start-rank, which causes a front-end handshake timeout per repo gotcha).
脚本与说明
来源记录日期 2026-06-27 · 此页面不重新认定硬件验证结果