From 46a544e0a067a7c88a2470e55dbee19a6c110873 Mon Sep 17 00:00:00 2001 From: zijiexia <37504505+zijiexia@users.noreply.github.com> Date: Thu, 27 Aug 2026 12:16:35 -0700 Subject: [PATCH] [Docs] GLM-5.3-Flash: point at compute-mamba-ratio for the KDA/KV pool split (#36719) Co-authored-by: Claude Opus 5 --- docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx b/docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx index 26d104d37..61e4227a4 100644 --- a/docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx +++ b/docs/cookbook/autoregressive/GLM/GLM-5.3-Flash.mdx @@ -35,6 +35,10 @@ import { benchmarks } from "/src/snippets/configs/zai-org/glm-5.3-flash-benchmar + +Generated commands leave `--mamba-full-memory-ratio` at its `0.9` default, which is a generic starting point rather than a workload-tuned split: too low starves the KDA state pool and clamps `max_running_requests`, too high over-provisions it and shrinks the KV pool. Use the repo-local [`compute-mamba-ratio`](https://github.com/sgl-project/sglang/blob/main/.claude/skills/compute-mamba-ratio/SKILL.md) skill to compute the balanced ratio — or the `--max-mamba-cache-size` pin to use instead — from your average request length and the two pool sizes printed in one boot log. See [Size both memory pools](#size-both-memory-pools) for what each pool caps. + + ## Playground Use the Playground for lower-level tuning such as attention parallelism, MoE communication, and reasoning or tool parsers. It inherits every selection from the deployment panel and shows only the command-line diff.