minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 13 Packages Projects Releases Wiki Activity

docs: mark Ling-3.0-flash DSPARK verified for all four quantizations on H200 (#36204)

Browse Source
This commit is contained in:
Xinyuan Tong
2026-08-25 02:05:32 +08:00
committed by GitHub
parent 5030637c65
commit 6e2f87d589
3 changed files with 56 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/configs/inclusionAI/ling-3.0-flash-benchmarks.jsx
+24
View File
@@ -16,6 +16,12 @@ export const benchmarks = [
sglang_version: "PR #33561 @ c5071ded",
accuracy: { gsm8k_pct: 96.59 },
},
{
match: { hw: "h200", variant: "default", quant: "bf16", strategy: "low-latency", spec: "dspark", nodes: "single" },
sglang_version: "PR #33561 @ 76a3e673",
accuracy: { gsm8k_pct: 96.36 },
notes: "Full GSM8K stop rate 99.62%; accept length ~4.5-5.1.",
},
{
// Rejected by the full GSM8K gate at request 1319: a no-EOS runaway generated
// >33k tokens. Recipe stays `verified: false` in ling-3.0-flash.jsx.
@@ -37,6 +43,24 @@ export const benchmarks = [
sglang_version: "PR #33561 @ e57e030b",
accuracy: { gsm8k_pct: 96.51 },
},
{
match: { hw: "h200", variant: "default", quant: "fp8", strategy: "low-latency", spec: "dspark", nodes: "single" },
sglang_version: "PR #33561 @ 76a3e673",
accuracy: { gsm8k_pct: 96.13 },
notes: "Full GSM8K stop rate 99.55%; accept length ~3.3-4.4.",
},
{
match: { hw: "h200", variant: "default", quant: "int4", strategy: "low-latency", spec: "dspark", nodes: "single" },
sglang_version: "PR #33561 @ 76a3e673",
accuracy: { gsm8k_pct: 96.36 },
notes: "Full GSM8K stop rate 99.62%; accept length ~4.6-4.9.",
},
{
match: { hw: "h200", variant: "default", quant: "mxfp4", strategy: "low-latency", spec: "dspark", nodes: "single" },
sglang_version: "PR #33561 @ 76a3e673",
accuracy: { gsm8k_pct: 96.29 },
notes: "Full GSM8K stop rate 99.85%; accept length ~3.8-5.9.",
},
{
match: { hw: "h200", variant: "default", quant: "int4", strategy: "high-throughput", spec: "off", nodes: "single" },
sglang_version: "PR #33561 @ e1a24a18",
docs/src/snippets/configs/inclusionAI/ling-3.0-flash.jsx
+31 -1
View File
@@ -187,6 +187,9 @@ sgl-eval run gsm8k \\
match: { ...cell.match, spec: "dspark" },
flags: cell.flags.flatMap((f) => (f === "--speculative-algorithm NEXTN" ? DSPARK_FLAGS : [f])),
});
// hw|quant pairs with a measured full-GSM8K DSPARK run; see the mdx
// DSPARK tip for scores and stop rates.
const DSPARK_VERIFIED = new Set(["b200|bf16", "h200|bf16", "h200|fp8"]);
const lowLatencyCells = [
{
match: { hw: "h20-3e", variant: "default", quant: "bf16", strategy: "low-latency", spec: "nextn", nodes: "single" },
@@ -342,8 +345,35 @@ sgl-eval run gsm8k \\
return [
...lowLatencyCells.flatMap((c) => [
c,
dsparkTwin(c, c.match.hw === "b200" && c.match.quant === "bf16"),
dsparkTwin(c, DSPARK_VERIFIED.has(`${c.match.hw}|${c.match.quant}`)),
]),
// INT4/MXFP4 have no NEXTN low-latency cell (their twin source), so the
// DSPARK legs validated on 4xH200 are listed directly.
{
match: { hw: "h200", variant: "default", quant: "int4", strategy: "low-latency", spec: "dspark", nodes: "single" },
verified: true,
flags: [
"--model-path {{MODEL_NAME}}",
"--tp 2",
...DSPARK_FLAGS,
"--mem-fraction-static 0.85",
"--host {{HOST_IP}}",
"--port {{PORT}}",
],
},
{
match: { hw: "h200", variant: "default", quant: "mxfp4", strategy: "low-latency", spec: "dspark", nodes: "single" },
verified: true,
flags: [
"--model-path {{MODEL_NAME}}",
"--tp 2",
"--moe-runner-backend flashinfer_mxfp4",
...DSPARK_FLAGS,
"--mem-fraction-static 0.85",
"--host {{HOST_IP}}",
"--port {{PORT}}",
],
},
{
match: { hw: "h20-3e", variant: "default", quant: "bf16", strategy: "high-throughput", spec: "off", nodes: "single" },
verified: false,