huangyanpei/VLA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
41 Commits 1 Branch 0 Tags
6764e8f12f320819e86d5476b3ed68fb8f45b43c
Commit Graph
11 Commits
Author SHA1 Message Date
Zihan Gao 6764e8f12f fix normalization (#112)
Pre-commit / pre-commit (push) Canceled after 0s
Details
2026-07-21 15:15:48 +08:00
Starrick Liu 72834e7de5 Update Wall-X to 1.1.0 (#104) 2026-06-15 11:40:00 +08:00
suolyerandyangping d18fa65fa1 add mot (#83) 
* add mot

* update libero example

* translate zh to en

* fix load model from hf

* lint

* lint

---------

Co-authored-by: yangping <yangping@x2robot.com>
 2026-02-03 11:35:25 +08:00
phoenixDongandfarmer 908329d214 [Serving] Update the details of the inference service (#70) 
* Update the details of the inference service startup

* add functions to compute and update robot-specific action/state normalization stats

* Update for pre-commit

* Union compute_action_statistics code into update_action_statistics

* Update for pre-commit

* Add default value for dof_config and agent_pos_config

---------

Co-authored-by: farmer <farmer@x2robot.com>
 2025-11-27 19:21:49 +08:00
Tong WuandGeoffrey19 7b57b7800b Fixed the bug in flow matching (#68) 
* fix a bug in flow matching

* fixed the bugs in flow matching

* fixed format

---------

Co-authored-by: Geoffrey19 <sympathischmann35@gmail.com>
 2025-11-07 15:11:49 +08:00
Lufang Chen 722335e428 Enable inference serving && fix train stability (#59) 
* enable serving

* lint

* update

* update
 2025-10-26 16:02:34 +08:00
Lufang Chen d821b0cb26 Fix normalizer (#57) 
* fix normalizer

* fix val

* update compute stats

* delete norm

* update readme

* minor fix

* fix action normalizer

* fix

* fix

* update

* update

* update

* update

* update

* lint

* lint

* lint

* lint
 2025-10-24 17:29:12 +08:00
Starrick Liu 421db17d53 feat: Major optimization and robustness improvements (#31) 
This release introduces significant performance optimizations, memory efficiency
improvements, and enhanced system robustness:

🚀 Performance Optimizations:
- Add three new fused CUDA kernels (rope_index, rot_pos_emb, get_window_index)
  for accelerated multimodal preprocessing
- Implement FSDP2 support for distributed training with improved memory efficiency
- Add Torch.compile integration for additional performance gains
- Optimize memory usage: reduce peak allocation from 48GB to 24GB on 8-GPU setup

🔧 System Robustness:
- Fix missing token position inputs in prediction pipeline
- Add type-robust negation operations in RoPE CUDA kernels (half/bfloat16 support)
- Fix dataset root parameter initialization in LeRobot data loader
- Enhanced error handling and input validation across fusion operators

📚 Documentation & Usability:
- Add comprehensive memory usage benchmarks and hardware recommendations
- Update citation format with proper arXiv reference
- Improve training configuration documentation with quick start guide
- Add detailed API documentation for new fusion operators

🛠️ Technical Details:
- Version bump to 1.0.1
- New CUDA kernels: rope_index.cu, rot_pos.cu, window_index.cu
- FSDP2 state dict loading with distribute_tensor support
- Enhanced multimodal RoPE with 3D position encoding
- Window attention optimization for Vision Transformers

Breaking Changes: None - all changes are backward compatible
 2025-09-17 23:09:20 +08:00
Lufang Chen e9332a283d [lint] Update lint (#16) 
* update lint

* update readme

* update ruff lint
 2025-09-11 13:18:33 +08:00
vincentchen ff1feb611f fix load model 2025-09-08 21:58:59 +08:00
Starrick 24dbdbd24b Init 2025-09-07 14:59:17 +08:00