minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[diffusion] doc: document verified GB300 and derived GB200 H3 recipes (#38296)

Browse Source
This commit is contained in:
Mick
2026-09-07 16:32:29 +08:00
committed by GitHub
parent b5766336d4
commit ba6d3df69a
3 changed files with 93 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/configs/MiniMaxAI/minimax-h3.jsx
+12 -5
View File
@@ -147,6 +147,8 @@ return {
supportedHardware: [
"b200",
"b300",
"gb300",
"gb200",
"h200",
"h100",
"mi300x",
@@ -550,6 +552,8 @@ return {
{ id: "b200-fsdp-4", hw: "b200", nodes: 1, gpus_per_node: 4, placement: "fsdp", tp_size: 1, ulysses_degree: 4, ring_degree: 1, encoder: "auto" },
{ id: "b300-resident-8", hw: "b300", nodes: 1, gpus_per_node: 8, placement: "resident", tp_size: 1, ulysses_degree: 8, ring_degree: 1, encoder: "auto", default: true },
{ id: "b300-fsdp-8", hw: "b300", nodes: 1, gpus_per_node: 8, placement: "fsdp", tp_size: 1, ulysses_degree: 8, ring_degree: 1, encoder: "auto" },
{ id: "gb300-resident-4", hw: "gb300", nodes: 1, gpus_per_node: 4, placement: "resident", tp_size: 1, ulysses_degree: 4, ring_degree: 1, encoder: "auto", default: true },
{ id: "gb200-resident-4", hw: "gb200", nodes: 1, gpus_per_node: 4, placement: "resident", tp_size: 1, ulysses_degree: 4, ring_degree: 1, encoder: "auto", default: true, unverified: true },
{ id: "h200-resident-4", hw: "h200", nodes: 1, gpus_per_node: 4, placement: "resident", tp_size: 1, ulysses_degree: 4, ring_degree: 1, encoder: "auto", default: true },
{ id: "h200-fsdp-4", hw: "h200", nodes: 1, gpus_per_node: 4, placement: "fsdp", tp_size: 1, ulysses_degree: 4, ring_degree: 1, encoder: "auto" },
{ id: "h200-cross-node-16", hw: "h200", nodes: 2, gpus_per_node: 8, placement: "resident", tp_size: 1, ulysses_degree: 8, ring_degree: 2, encoder: "replicate" },
@@ -673,9 +677,12 @@ return {
|| (s.precision === "fp8" && ["b200", "b300"].includes(s.hw));
const executionVerified = s.execution === "eager"
|| (s.execution === "bcg" && ["b200", "h200"].includes(s.hw) && s.weights === "ref2va");
const checkpointVerified = s.hw !== "gb300" || s.weights === "fl2va";
const serveVerified = topologyVerified && encoderVerified && attentionVerified
&& precisionVerified && executionVerified;
const requestVerified = topologyVerified && (["lossless", "extra-high"].includes(s.quality)
&& precisionVerified && executionVerified && checkpointVerified;
const requestCovered = s.hw !== "gb300" || (serveVerified && s.weights === "fl2va"
&& s.mode === "t2va" && s.quality === "lossless" && Number(s.outputs) === 1);
const requestVerified = topologyVerified && requestCovered && (["lossless", "extra-high"].includes(s.quality)
|| (s.quality === "high" && highAudited && s.execution === "eager"));
const topologyParts = [];
@@ -712,7 +719,7 @@ return {
let automaticAttention = "FlashAttention (auto)";
if (["mi300x", "mi355x"].includes(s.hw)) {
automaticAttention = "AITER (auto)";
} else if (topology.ring_degree === 1 && ["b200", "b300"].includes(s.hw)) {
} else if (topology.ring_degree === 1 && ["b200", "b300", "gb200", "gb300"].includes(s.hw)) {
automaticAttention = "Dynamic cuDNN / FA (auto)";
} else if (topology.ring_degree === 1 && ["rtx5090", "rtx4090"].includes(s.hw)) {
automaticAttention = "Torch SDPA (auto)";
@@ -964,9 +971,9 @@ return {
? `bash -lc 'python -m pip install -e "/sgl-workspace/sglang/python[diffusion_hip]" && exec sglang serve "$@"' --`
: `bash -lc 'python -m pip install -e "/sgl-workspace/sglang/python[diffusion]" && exec sglang serve "$@"' --`,
// Publish AMD Docker only after an H3-capable ROCm image has been validated.
// Publish Docker only after the platform's H3 image/command has been validated.
runModes: (s) =>
["mi300x", "mi355x"].includes(s.hw)
["mi300x", "mi355x", "gb200", "gb300"].includes(s.hw)
? ["python"]
: ["python", "docker"],