Skip to content

Support remote InternVLA eval and GPU-mapped X-VLA launch#3

Open
kew6688 wants to merge 1 commit into
mainfrom
baselines_fix
Open

Support remote InternVLA eval and GPU-mapped X-VLA launch#3
kew6688 wants to merge 1 commit into
mainfrom
baselines_fix

Conversation

@kew6688
Copy link
Copy Markdown
Collaborator

@kew6688 kew6688 commented May 18, 2026

  • Add remote EvalClient URL, token, and run_id support to InternVLA-A1
  • Serialize InternVLA action/base outputs before sending to EvalClient
  • Add EvalClient recovery on InternVLA step failures
  • Document InternVLA single-worker, multi-worker, and CLI usage
  • Allow run_xvla_eval.sh to assign workers to CUDA_VISIBLE_DEVICES
  • Update X-VLA genmanip-client install extra

- Add remote EvalClient URL, token, and run_id support to InternVLA-A1
- Serialize InternVLA action/base outputs before sending to EvalClient
- Add EvalClient recovery on InternVLA step failures
- Document InternVLA single-worker, multi-worker, and CLI usage
- Allow run_xvla_eval.sh to assign workers to CUDA_VISIBLE_DEVICES
- Update X-VLA genmanip-client install extra
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant