Skip to content

[Model/VLA] Support MiniCPM-RobotManip#26164

Draft
tc-mb wants to merge 2 commits into
ggml-org:masterfrom
tc-mb:Support-MiniCPM-RobotManip
Draft

[Model/VLA] Support MiniCPM-RobotManip#26164
tc-mb wants to merge 2 commits into
ggml-org:masterfrom
tc-mb:Support-MiniCPM-RobotManip

Conversation

@tc-mb

@tc-mb tc-mb commented Jul 27, 2026

Copy link
Copy Markdown
Contributor

Purpose
Add support for the MiniCPM-RobotManip 1.5B VLA model.

  • Add an experimental VLA runtime, libvla
  • Introduce MiniCPM-RobotManip as the first supported model
  • Convert and load the action head as a standalone GGUF file
  • Generate robot control sequences from final libllama hidden states
  • Provide llama-vla-cli
  • Add the /v1/vla/predictions server endpoint
  • Add GGUF reload and numerical consistency checks

tc-mb added 2 commits July 25, 2026 14:42
Signed-off-by: tc-mb <tianchi_cai@icloud.com>
Signed-off-by: tc-mb <tianchi_cai@icloud.com>
@github-actions github-actions Bot added documentation Improvements or additions to documentation build Compilation issues server mtmd Related to multimodal functionality (video/image/audio) labels Jul 27, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

build Compilation issues documentation Improvements or additions to documentation mtmd Related to multimodal functionality (video/image/audio) server

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant