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

[NPU] [DOC] Rename NPU hardware to Ascend A2/A3 Series product (#39389)

Browse Source
This commit is contained in:
amote-i
2026-09-15 10:33:14 +08:00
committed by GitHub
parent 5dde6e8f02
commit bdf8886ad3
66 changed files with 759 additions and 759 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/_deployment.jsx
+3 -3
View File
@@ -147,10 +147,10 @@ export const Deployment = ({ config, benchmarks }) => {
{ id: "mi355x", label: "MI355X", vram: "288GB",
multiNodeDockerFlags: [...AMD_RDMA_DOCKER_FLAGS] },
],
// Atlas 800I A3 (910C): 1 card = 2 dies, so --tp-size is 2× the card
// Ascend A3 Series: 1 card = 2 dies, so --tp-size is 2× the card
// count (32 cards -> --tp-size 64).
npu: [
{ id: "a3", label: "Atlas 800I A3", vram: "64GB/die" },
{ id: "a3", label: "Ascend A3 Series", vram: "64GB/die" },
],
};
@@ -839,7 +839,7 @@ export const Deployment = ({ config, benchmarks }) => {
: vendorOf(sel.hw) === "npu"
? [
// NPU: --privileged grants the davinci devices (16 dies on an
// 8-card Atlas 800I A3 node); the host CANN driver/firmware/state
// 8-card Ascend A3 Series node); the host CANN driver/firmware/state
// must be mounted in.
"docker run --privileged --shm-size=16g",
" --device=/dev/davinci0 --device=/dev/davinci1 --device=/dev/davinci2 --device=/dev/davinci3",
docs/src/snippets/_playground.jsx
+1 -1
View File
@@ -772,7 +772,7 @@ export const Playground = ({ config }) => {
&& (!mmOpt.excludesStrategy || !mmOpt.excludesStrategy.includes(base.strategy));
const backendIsMega = slotDisplay("backend") === "megamoe";
// `ep.showWhen` (function of base) drops the whole EP select on bases
// where EP is not a supported lever (e.g. the single-shape A3 recipe).
// where EP is not a supported lever (e.g. the single-shape A3 Series recipe).
const epShown = !!fc.ep
&& !(typeof fc.ep.showWhen === "function" && !fc.ep.showWhen(base));
return (
docs/src/snippets/configs/moonshotai/kimi-k3.jsx
+5 -5
View File
@@ -198,7 +198,7 @@ export const config = {
disableReason: (s) => (s.hw === "a3" ? "Only Modelslim (W4A8) is supported on this recipe." : ""),
},
{
// A3 only (NPU W4A8 checkpoint); hidden on the GPU recipes.
// A3 Series only (NPU W4A8 checkpoint); hidden on the GPU recipes.
id: "modelslim",
label: "Modelslim (W4A8)",
subtitle: "ModelScope NPU checkpoint",
@@ -513,7 +513,7 @@ export const config = {
]; },
},
{
// A3 only: 64 ranks (4 nodes × 8 cards × 2 dies); hidden on the GPU recipes.
// A3 Series only: 64 ranks (4 nodes × 8 cards × 2 dies); hidden on the GPU recipes.
value: 64,
hide: { hw: ["b300", "gb300", "b200", "gb200", "h200", "h100", "mi350x", "mi355x"] },
},
@@ -719,7 +719,7 @@ export const config = {
// EAGLE --speculative-num-steps N (chain; topk>1 is a tree)
// Only DSPARK is selectable today, so only its form is emitted.
id: "proposedDraftTokens", title: "Proposed Draft Tokens",
// The A3 recipe pins the shipped block size (7).
// The A3 Series recipe pins the shipped block size (7).
showWhen: (b) => b.spec === "dspark" && b.hw !== "a3",
control: "slider",
stripPrefixes: [
@@ -743,7 +743,7 @@ export const config = {
// Spec-only, so gate the row on DSPARK; every DSPARK recipe (except the PD
// prefill role) turns it on in the base, so this row derives to On and
// exists mainly as the opt-out.
// Needs the Triton linear-attn decode backend (the K3 default); the A3
// Needs the Triton linear-attn decode backend (the K3 default); the A3 Series
// script never sets it.
id: "replaySsm", title: "ReplaySSM (spec)",
showWhen: (b) => b.spec === "dspark" && b.hw !== "a3",
@@ -766,7 +766,7 @@ export const config = {
// without --speculative-dspark-sps-table-path (every step still
// verifies full width); fails fast with ReplaySSM or DCP > 1.
id: "raggedVerify", title: "Ragged Verify Mode (spec)",
// The A3 recipe pins static.
// The A3 Series recipe pins static.
showWhen: (b) => b.spec === "dspark" && b.hw !== "a3",
stripEnv: ["SGLANG_RAGGED_VERIFY_MODE"],
options: [
docs/src/snippets/diffusion/flux-deployment.jsx
+4 -4
View File
@@ -14,8 +14,8 @@ export const FluxDeployment = () => {
{ id: 'mi355x', label: 'MI355X', default: false },
{ id: 'mi325x', label: 'MI325X', default: false },
{ id: 'mi300x', label: 'MI300X', default: false },
{ id: 'a2', label: 'A2', default: false },
{ id: 'a3', label: 'A3', default: false }
{ id: 'a2', label: 'A2 Series', default: false },
{ id: 'a3', label: 'A3 Series', default: false }
]
},
version: {
@@ -51,7 +51,7 @@ export const FluxDeployment = () => {
}
if (hardware === 'a3') {
return `#One A3 card has 2 npu chips
return `#One A3 Series card has 2 npu chips
sglang serve \\
--tp-size 2 \\
--model-path ${config.repoId} \\
@@ -133,7 +133,7 @@ sglang serve \\
useEffect(() => {
const isAscend = values.hardware === 'a2' || values.hardware === 'a3';
const targetTabName = isAscend ? 'Ascend A3' : 'NVIDIA B200';
const targetTabName = isAscend ? 'Ascend A3 Series' : 'NVIDIA B200';
const allTabs = document.querySelectorAll('button, [role="tab"]');
allTabs.forEach((tab) => {
docs/src/snippets/diffusion/qwen-image-deployment.jsx
+5 -5
View File
@@ -14,8 +14,8 @@ export const QwenImageDeployment = () => {
{ id: 'mi300x', label: 'MI300X', default: false },
{ id: 'mi325x', label: 'MI325X', default: false },
{ id: 'mi355x', label: 'MI355X', default: false },
{ id: 'a2', label: 'A2', default: false },
{ id: 'a3', label: 'A3', default: false }
{ id: 'a2', label: 'A2 Series', default: false },
{ id: 'a3', label: 'A3 Series', default: false }
]
},
precision: {
@@ -42,7 +42,7 @@ export const QwenImageDeployment = () => {
}
if (values.hardware === 'a3') {
return `#One A3 card has 2 npu chips
return `#One A3 Series card has 2 npu chips
sglang serve \\
--model-path Qwen/Qwen-Image \\
--tp-size 1 \\
@@ -131,8 +131,8 @@ sglang serve \\
useEffect(() => {
let targetTabName = 'AMD MI300X';
if (values.hardware === 'a2') targetTabName = 'Ascend A2';
if (values.hardware === 'a3') targetTabName = 'Ascend A3';
if (values.hardware === 'a2') targetTabName = 'Ascend A2 Series';
if (values.hardware === 'a3') targetTabName = 'Ascend A3 Series';
const allTabs = document.querySelectorAll('button, [role="tab"]');
docs/src/snippets/diffusion/wan21-deployment.jsx
+4 -4
View File
@@ -47,8 +47,8 @@ export const Wan21Deployment = () => {
{ id: 'mi300x', label: 'MI300X', default: false },
{ id: 'mi325x', label: 'MI325X', default: false },
{ id: 'mi355x', label: 'MI355X', default: false },
{ id: 'a2', label: 'A2', default: false },
{ id: 'a3', label: 'A3', default: false }
{ id: 'a2', label: 'A2 Series', default: false },
{ id: 'a3', label: 'A3 Series', default: false }
],
},
task: {
@@ -119,7 +119,7 @@ export const Wan21Deployment = () => {
useEffect(() => {
const isAscend = values.hardware === 'a2' || values.hardware === 'a3';
const targetTabName = isAscend ? 'Ascend A3' : 'NVIDIA B200';
const targetTabName = isAscend ? 'Ascend A3 Series' : 'NVIDIA B200';
const allTabs = document.querySelectorAll('button, [role="tab"]');
@@ -182,7 +182,7 @@ export const Wan21Deployment = () => {
if (hardware === 'a2' || hardware === 'a3') {
const comment = hardware === 'a3'
? '#One A3 card has 2 npu chips\n'
? '#One A3 Series card has 2 npu chips\n'
: '';
const isBestPractice = bestPractice === 'on';
let command;
docs/src/snippets/diffusion/wan22-deployment.jsx
+4 -4
View File
@@ -11,8 +11,8 @@
{ id: 'mi300x', label: 'MI300X', default: false },
{ id: 'mi325x', label: 'MI325X', default: false },
{ id: 'mi355x', label: 'MI355X', default: false },
{ id: 'a2', label: 'A2', default: false },
{ id: 'a3', label: 'A3', default: false }
{ id: 'a2', label: 'A2 Series', default: false },
{ id: 'a3', label: 'A3 Series', default: false }
],
},
task: {
@@ -90,7 +90,7 @@
useEffect(() => {
const isAscend = values.hardware === 'a2' || values.hardware === 'a3';
const targetTabName = isAscend ? 'Ascend A3' : 'NVIDIA B200';
const targetTabName = isAscend ? 'Ascend A3 Series' : 'NVIDIA B200';
const allTabs = document.querySelectorAll('button, [role="tab"]');
@@ -138,7 +138,7 @@
if (hardware === 'a2' || hardware === 'a3') {
const comment = hardware === 'a3'
? '#One A3 card has 2 npu chips\n'
? '#One A3 Series card has 2 npu chips\n'
: '';
const isBestPractice = bestPractice === 'on';
let command;
docs/src/snippets/diffusion/zimage-turbo-deployment.jsx
+4 -4
View File
@@ -13,8 +13,8 @@ export const ZImageTurboDeployment = () => {
{ id: 'b200', label: 'B200', default: true },
{ id: 'h200', label: 'H200', default: false },
{ id: 'h100', label: 'H100', default: false },
{ id: 'a2', label: 'A2', default: false },
{ id: 'a3', label: 'A3', default: false }
{ id: 'a2', label: 'A2 Series', default: false },
{ id: 'a3', label: 'A3 Series', default: false }
]
}
},
@@ -29,7 +29,7 @@ export const ZImageTurboDeployment = () => {
}
if (hardware === 'a3') {
return `#One A3 card has 2 npu chips
return `#One A3 Series card has 2 npu chips
sglang serve \\
--model-path Tongyi-MAI/Z-Image-Turbo \\
--tp-size 2 \\
@@ -112,7 +112,7 @@ sglang serve \\
useEffect(() => {
const isAscend = values.hardware === 'a2' || values.hardware === 'a3';
const targetTabName = isAscend ? 'Ascend A2 / A3' : 'AMD MI300X';
const targetTabName = isAscend ? 'Ascend A2/A3 Series' : 'AMD MI300X';
const allTabs = document.querySelectorAll('button, [role="tab"]');
allTabs.forEach((tab) => {