LogoClawIndex
CasesSkillsAbout
LogoClawIndex

graph-mode-internals - LMdeploy graph mode architecture

Explains how graph mode captures and replays compute sequences for decode steps, covering runner architecture, buffer management, and vendor differences.

Tags

Updated: 2026-06-30
graph modeinferenceperformancerunnerbuffervendor

Capabilities

capture graphreplay graphallocate buffersfill buffers

Typical Inputs

batch sizegraph metadatamodel

Typical Outputs

hidden statestokens

What this skill does

  • capture graph
  • replay graph
  • allocate buffers
  • fill buffers
  • update context
  • get outputs
  • compare vendors

Inputs

  • batch size
  • graph metadata
  • model
  • device

Outputs

  • hidden states
  • tokens

Requirements

  • CUDA support
  • NPU support
  • CUDA graph runner
  • NPU graph runner

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.