Embodied · vla · wam · vla.policy_rollout · wam.world_action_modeling

StarVLA

WorldFoundry runtime executed official StarVLA QwenOFT predict_action with local Qwen3-VL-OFT-LIBERO-4in1 checkpoint and Qwen3-VL-4B base VLM on an 80GB CUDA GPU.

Runner verified统一环境源码已固定starvla

构建运行命令

选择仓库中已记录的 variant，然后复制对应的准备、检查或运行命令。

worldfoundry.pipeline

Variant

任务vla.policy_rollout

环境worldfoundry-unified-cu128

设备CUDA 12.8

worldfoundry-eval evaluate \
  --mode model \
  --model-id starvla-qwen3-vl-oft-libero-4in1 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/starvla-qwen3-vl-oft-libero-4in1 \
  --metric artifact_count \
  --json

兼容性与版本

由 Manifest 生成

集成状态: integrated
Runner 证据: verified
环境: worldfoundry-unified-cu128
Python: 3.10
CUDA: CUDA 12.8
PyTorch: torch
源码 revision: 1947454be8c0f4de315f4cbde96b874819a6dab3
Checkpoint revision: 1947454be8c0f4de315f4cbde96b874819a6dab3

Runtime profile: starvla
Pipeline binding: starvla
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.component_pipelines:StarVLAPipeline
Backend stage: in_tree_checkpoint_runtime
Runtime 状态: in_tree_qwen3_vl_oft_libero_predict_action_gpu_ready
Driver 状态: compatible
环境类型: 统一环境

安装环境

环境解析器会读取已记录 profile，并选择此处显示的统一或独立环境。

bash scripts/setup/model_env_install.sh --model starvla-qwen3-vl-oft-libero-4in1

依赖版本约束 14

numpy
Pillow
opencv-python
torch
torchvision
transformers
accelerate
safetensors
einops
qwen-vl-utils
decord
omegaconf
diffusers
rich

Conda 依赖 2

python
pip

Checkpoint 与资产

分配算力前先做本地检查；gated、private 与 license 字段直接来自 checkpoint manifest。

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

StarVLA/Qwen3-VL-OFT-LIBERO-4in1

Revision: 1947454be8c0f4de315f4cbde96b874819a6dab3
License: —
Gated: —
Private: —

StarVLA/WM4A-Wan2d2-OFT-LIBERO-4in1

Revision: e431aa1d059fd61864db707f3c178673af01c9d4
License: mit
Gated: —
Private: —

Qwen/Qwen3-VL-4B-Instruct

Revision: ebb281ec70b05090aa6165b016eac8ec08e71b17
License: —
Gated: —
Private: —

Wan-AI/Wan2.2-TI2V-5B-Diffusers

Revision: b8fff7315c768468a5333511427288870b2e9635
License: —
Gated: —
Private: —

运行与输出

生成的命令通过共享 evaluation 边界运行，并持久保存结果 manifest 与 artifact。

worldfoundry-eval evaluate \
  --mode model \
  --model-id starvla-qwen3-vl-oft-libero-4in1 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/starvla-qwen3-vl-oft-libero-4in1 \
  --metric artifact_count \
  --json

输入契约

字段	已记录契约
`actions`	robot_action, world_action, latent_action_tokens, action_space
`image`	Required
`instruction`	Required
`prompt`	Required
`video`	Required

Artifact 契约

Artifact 类型	文件名 / 路径
`action_trace`	`—`
`action_trace`	`starvla_action_trace.json`

证据与来源

Catalog 集成、原生 demo parity 与 runner parity 是三条独立记录。

集成状态: integrated
Runner 证据: verified
原生 Demo 证据: 未记录
验证 Imports: numpy, PIL, cv2, transformers, decord, diffusers, rich, qwen_vl_utils, omegaconf

配方溯源

worldfoundry/data/models/catalog/vla_va_wam/starvla.yamlGitHubhttps://github.com/starVLA/starVLAHugging Face1947454be8c0f4de315f4cbde96b874819a6dab3Hugging Facee431aa1d059fd61864db707f3c178673af01c9d4Hugging Facehttps://huggingface.co/Qwen/Qwen3-VL-4B-Instruct

构建运行命令

输入契约

Artifact 契约

相关配方