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

docs(cookbook): re-benchmark DeepSeek-V4 on sglang 0.5.15 (#31363)

Browse Source 
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
This commit is contained in:
Douglas Yang
2026-07-21 22:55:36 +00:00
committed by GitHub
co-authored by Claude Opus 4.8 Zijie Xia
parent 9057db9417
commit 4a55fdba0b
8 changed files with 231 additions and 71 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/cookbook-add-model/templates/benchmarks.jsx.tmpl
+2 -1
View File
@@ -7,7 +7,8 @@
// "pending" until an entry has a non-null speed metric or accuracy. Speed shape:
// speed: [{ workload: {dataset, isl, osl, max_concurrency}, ttft_ms, tpot_ms,
// tokens_per_sec_per_gpu }, ...]
// - ttft_ms/tpot_ms are P50 (median); set config.latencyPercentile ("P50" default, or "Mean").
// - ttft_ms/tpot_ms are P50 (median); set config.latencyPercentile ("P50" default, or "Mean");
// an entry-level latencyPercentile overrides the page value per cell.
// - tokens_per_sec_per_gpu = total (in+out) tok/s/GPU
// (= output tok/s ÷ GPUs × (isl+osl)/osl). interactivity is derived = 1000/TPOT (tokens/s/user).
// Per-cell `accuracy: { <key>: <pct> }` overrides the config's defaultAccuracy.