[docs] DeepSeek-V4 cookbook: note cu129 image for GB200 Pro DeepEP backend (#26413)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.7
parent
b66f8e0b96
commit
6afebc278a
@@ -909,6 +909,20 @@ export const DeepSeekV4Deployment = () => {
|
|||||||
`# NVSHMEM_HCA_LIST=<your-hca-list>\n` +
|
`# NVSHMEM_HCA_LIST=<your-hca-list>\n` +
|
||||||
cmd;
|
cmd;
|
||||||
}
|
}
|
||||||
|
// GB200 Pro with MegaMoE disabled runs the DeepEP a2a backend, which is
|
||||||
|
// currently only packaged in the CUDA 12.9 image — the default `:latest`
|
||||||
|
// ships CUDA 13 and does not include a compatible DeepEP build.
|
||||||
|
if (
|
||||||
|
hardware === "gb200" &&
|
||||||
|
isBig &&
|
||||||
|
megamoe === "disabled" &&
|
||||||
|
flags.some((f) => f.includes("--moe-a2a-backend deepep"))
|
||||||
|
) {
|
||||||
|
cmd =
|
||||||
|
`# NOTE: for the DeepEP backend, use the cu129 docker image\n` +
|
||||||
|
`# (lmsysorg/sglang:latest-cu129) instead of the default \`:latest\`.\n` +
|
||||||
|
cmd;
|
||||||
|
}
|
||||||
const withMultinode = multinode ? prependMultiNodeNote(cmd, nnodes) : cmd;
|
const withMultinode = multinode ? prependMultiNodeNote(cmd, nnodes) : cmd;
|
||||||
|
|
||||||
// H200 Pro low-latency: show BOTH a single-node (TP=8 marlin) variant
|
// H200 Pro low-latency: show BOTH a single-node (TP=8 marlin) variant
|
||||||
|
|||||||
Reference in New Issue
Block a user