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

[Docs] Fill GLM-5.2 H200 FP8 speed cells (low-latency, balanced); fix MTP notation (#31554)

Browse Source 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Han-Yin Chang
2026-08-14 13:56:55 -07:00
committed by GitHub
co-authored by Claude Fable 5
parent b676793e5e
commit 22dde1dd5b
2 changed files with 36 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cookbook/autoregressive/GLM/GLM-5.2.mdx
+1 -1
View File
@@ -57,7 +57,7 @@ import { benchmarks } from "/src/snippets/configs/zai-org/glm-5.2-benchmarks.jsx
</Warning>
<Note>
Speed numbers are measured with `--random-range-ratio 1.0`, `--flush-cache`, on `main @ 09ca4fc`. Spec cells pin the EAGLE acceptance length via the serve env `SGLANG_SIMULATE_ACC_LEN` (low-latency 5-1-6 = 3.5, balanced 2-1-3 = 2); high-throughput has no spec.
Speed numbers are measured with `--random-range-ratio 1.0`, `--flush-cache`, on `main @ 09ca4fc` (H200 FP8 cells: `v0.5.14 @ 49e384ce`). Spec cells pin the EAGLE acceptance length via the serve env `SGLANG_SIMULATE_ACC_LEN` (low-latency 5-1-6 = 3.5; FP8 balanced 1-1-2 = 2; NVFP4 balanced 2-1-3 = 2); high-throughput has no spec.
</Note>
## Playground