Embodied · vla · vla.policy_rollout · vlm_policy · robot_policy

RoboFlamingo

robovlms

RoboFlamingo/OpenFlamingo architecture and inference source are vendored in-tree; public pipeline CUDA action_trace validation passed.

Runner verifiedUnified environmentroboflamingo

Build your run

Choose a recorded variant, then copy the exact setup or inspection command.

worldfoundry.pipeline

Variant

Taskvla

Environmentworldfoundry-unified-cu128

DevicePrepare Only

worldfoundry-eval evaluate \
  --mode model \
  --model-id roboflamingo \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/roboflamingo \
  --metric artifact_count \
  --json

Compatibility & versions

Manifest-backed recipe

Integration: integrated
Runner evidence: verified
Environment: worldfoundry-unified-cu128
Python: 3.8
CUDA: Prepare Only
PyTorch: torch
Source revision: —
Checkpoint revision: —

Runtime profile: roboflamingo
Pipeline binding: roboflamingo
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.component_pipelines:RoboFlamingoPipeline
Backend stage: in_tree_runtime
Runtime status: in_tree_roboflamingo_predict_action_gpu_ready
Driver status: prepare_only_vlm_policy_runtime_requires_checkpoint_validation
Environment kind: Unified environment

Install environment

The environment resolver reads the recorded profile and chooses the unified or dedicated environment shown here.

bash scripts/setup/model_env_install.sh --model roboflamingo

Package constraints 14

numpy
Pillow
opencv-python
torch
torchvision
torchaudio
transformers
huggingface-hub
open-clip-torch
einops
einops-exts
pytorch-lightning
omegaconf
safetensors

Conda packages 3

python
pip
ffmpeg

Checkpoints & assets

Run the local check before allocating compute. Gated, private, and license fields below come directly from the checkpoint manifest.

worldfoundry-eval zoo model-download --model-id roboflamingo --check-local --json

robovlms/RoboFlamingo

Revision: —
License: —
Gated: —
Private: —

openflamingo/OpenFlamingo-3B-vitl-mpt1b-langinstruct

Revision: —
License: —
Gated: —
Private: —

anas-awadalla/mpt-1b-redpajama-200b-dolly

Revision: —
License: —
Gated: —
Private: —

Launch & outputs

The generated command uses the shared evaluation boundary and writes durable result manifests and artifacts.

worldfoundry-eval evaluate \
  --mode model \
  --model-id roboflamingo \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/roboflamingo \
  --metric artifact_count \
  --json

Input contract

Field	Recorded contract
`actions`	robot_action, action_space
`image`	Required
`instruction`	Required
`prompt`	Required
`video`	Required

Artifact contract

Artifact kind	Filename / path
`action_trace`	`—`
`action_trace`	`roboflamingo_action_trace.json`

Evidence & sources

Catalog integration, native-demo parity, and runner parity are independent records.

Integration: integrated
Runner evidence: verified
Native demo evidence: Not recorded
Validation imports: numpy, PIL, cv2, torch, transformers, open_clip

Recipe provenance

worldfoundry/data/models/catalog/vla_va_wam/roboflamingo.yamlGitHubhttps://github.com/RoboFlamingo/RoboFlamingo

Build your run

Input contract

Artifact contract

Related recipes