minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 10 Packages Projects Releases Wiki Activity

[Cookbook] Verify DeepSeek-V4 Flash Vision balanced and high-throughput on B200 (#37468)

Browse Source 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
zijiexia
2026-09-01 13:09:14 -07:00
committed by GitHub
co-authored by Claude Fable 5
parent 442c7c1e29
commit 0f18d389b4
2 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/src/snippets/configs/deepseek-ai/deepseek-v4-benchmarks.jsx
+12 -2
View File
@@ -653,8 +653,18 @@ export const benchmarks = [
accuracy: { mmmu_pro_pct: 75.14 },
notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×B200 (TP=4) at temperature 1.0, top-p 0.95, --reasoning-effort max, with the bundled DSpark head enabled (--speculative-algorithm DSPARK).",
},
{ match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
{ match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" } },
{
match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
sglang_version: "PR #37253 @ 31854c3",
accuracy: { mmmu_pro_pct: 74.10 },
notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×B200 (TP=4, DP=4, DeepEP) at temperature 1.0, top-p 0.95, --reasoning-effort max; target-only (DP Attention is incompatible with DSpark).",
},
{
match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
sglang_version: "PR #37253 @ 31854c3",
accuracy: { mmmu_pro_pct: 73.76 },
notes: "MMMU-Pro (standard, 10-option) measured with sgl-eval on 4×B200 (TP=4, DP=4, MegaMoE) at temperature 1.0, top-p 0.95, --reasoning-effort max; target-only (DP Attention is incompatible with DSpark).",
},
// B300 / GB200 / GB300 / H200 / H100 — Flash Vision (Exp), all pending
{ match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "low-latency", nodes: "single" } },
{ match: { hw: "b300", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" } },
docs/src/snippets/configs/deepseek-ai/deepseek-v4.jsx
+2 -4
View File
@@ -3047,8 +3047,7 @@ sgl-eval run mmmu_pro \\
},
{
match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "balanced", nodes: "single" },
verified: false,
verificationStatus: "in-progress",
verified: true,
warn: "DeepSeek-V4-Flash-Vision-Exp support has not shipped in an SGLang release yet (sglang PR 37253): Docker mode already points at the preview image; for Python mode install SGLang from that PR. See [Flash Vision notes](#vision-note).",
env: ["SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=1024"],
flags: [
@@ -3065,8 +3064,7 @@ sgl-eval run mmmu_pro \\
},
{
match: { hw: "b200", variant: "flash-vision", quant: "fp4", strategy: "high-throughput", nodes: "single" },
verified: false,
verificationStatus: "in-progress",
verified: true,
warn: "DeepSeek-V4-Flash-Vision-Exp support has not shipped in an SGLang release yet (sglang PR 37253): Docker mode already points at the preview image; for Python mode install SGLang from that PR. See [Flash Vision notes](#vision-note).",
env: [
"SGLANG_OPT_DEEPGEMM_MEGA_MOE_NUM_MAX_TOKENS_PER_RANK=8320",