change project config files to prepare public deployment

.gitmodules

 [submodule "batchASE"]
 	path = batchASE
-	url = ssh://git@10.208.16.64:2222/wangleping/mace-bench-hygon.git
+	url = git@gitee.com:nivren/batch-ase.git
 	branch = hygon-opt-bfgs
 [submodule "mace"]
 	path = 3rdparty/mace
-	url = ssh://git@10.208.16.64:2222/huafeng/MACE.git
+	url = git@gitee.com:nivren/mace.git
 	branch = fasteq-mace-bench
 [submodule "FastEq"]
 	path = 3rdparty/FastEq
-	url = ssh://git@10.208.16.64:2222/ncic-ai4sci/FastEq.git
+	url = git@gitee.com:nivren/fast-eq.git
 	branch = hip
 [submodule "cuequivariance_torch"]
 	path = 3rdparty/cuequivariance_torch
-	url = git@github.com:malixian/cuEquivariance.git
+	url = git@gitee.com:nivren/fast-eq.git
 	branch = hip

README.md

-# BOMLIP-CSP
+# ICT-CSP
 
 An open-source Python framework that integrates machine learning interatomic
 potentials (MLIPs) with a tailored batched optimization strategy, enabling rapid,
-unbiased structure prediction across the full density range
+unbiased structure prediction across the full density range.
 
+## Installation (Hygon DCU)
+
+### 1. Clone the repository
 
-## Install the BOMLIP-CSP
 ```sh
-git clone https://github.com/pic-ai-robotic-chemistry/BOMLIP-CSP.git --recursive
-conda create -n BOMLIP_CSP python=3.10 -y
-conda activate BOMLIP_CSP
-cd BOMLIP-CSP/batchASE
-# using chmod -R 755 in your BOMLIP-CSP folder if you do not have exection permission
-./reproduce/init_mace.sh
-source util/env.sh
-cd ..
+git clone -b public git@gitee.com:nivren/ict-csp.git
+cd ict-csp
 ```
 
-## Perform a complete CSP process
+### 2. Configure local torch & triton wheels
 
-Starting the exclusive mode to further accelerate the process if you have administrator privileges.
-```sh
-sudo ./util/mps_start.sh
-```
+Edit `pyproject.toml` — replace the paths under `[tool.uv.sources]` for `torch` and
+`triton` with the local `.whl` file paths for your DCU platform.
 
-The main program of the CSP process.
+### 3. Fetch third-party submodules
 
-BATCHED GEOMETRY OPTIMIZATION REQUIRES GPU USAGE!
-PLEASE CONFIRM THE GPU AND WORKER SETTINGS IN THE SHELL SCRIPT BEFORE RUNNING THIS COMMAND!
-which includes --gpu_offset --n_gpus --num_workers.
 ```sh
-./csp.sh
+git submodule update --init \
+  batchASE \
+  3rdparty/mace \
+  3rdparty/FastEq \
+  3rdparty/cuequivariance_torch
 ```
 
-End the exclusive mode after running.
+### 4. Set up build dependencies
+
 ```sh
-sudo ./util/mps_clean.sh
+source /opt/dtk/env.sh
+
+sudo apt install python3.10-dev python3-dev
+sudo apt install libgflags-dev libgoogle-glog-dev
+sudo apt install build-essential libstdc++-12-dev
+sudo ln -s /usr/lib/x86_64-linux-gnu/librt.so.1 /usr/lib/x86_64-linux-gnu/librt.so
 ```
 
-## Perform conformer search / structure generation / structure optimization separately
-### conformer search
-In csp.sh, the argument --mode controls the jobs to do.
+### 5. Create the virtual environment
+
+> **Prerequisite:** This project uses [uv](https://docs.astral.sh/uv/) for Python
+> environment management. Install it first if you haven't:
+> ```sh
+> curl -LsSf https://astral.sh/uv/install.sh | sh
+> ```
 
-Use conformer_only to perform conformer search task only.
-```sh
-python "${TOP_DIR}/main.py" --path ${TAR_DIR} --smiles "C1CC2=COC=C12" \
-     --num_generation 100 --generate_conformers 10 --mode conformer_only > generate_conformer.log 2>&1
-```
-### structure generation
-Or use structure_only to perform structure generation only.
-In this mode, conformers (generated by this program or provided by yourself as .xyz file from other methods) should be provided in folder ${TAR_DIR}/molecule_${i}/conformers as conformer_${j}.xyz files
-where i start from 1 and j start from 0.
 ```sh
-python "${TOP_DIR}/main.py" --path ${TAR_DIR} --molecule_num_in_cell 1 \
-     --space_group_list 14,61 --add_name XULDUD --max_workers 16 --num_generation 100 \
-     --use_conformers 4 --mode structure_only > generate_structure.log 2>&1
+uv sync
 ```
-Conformer search and structure generation could also be done in python script with higher freedom (e.g. higher Z', higher-order co-crystal or control trail structure number for each space group), see structure_generate.py.
 
-### structure optimization
-Structure optimization is done by a seperate command
+### 6. Verify the installation
+
 ```sh
-python "${TOP_DIR}/batchASE/scripts/opt_batch.py" ...
+uv run python -c "import torch, ase, mace, fasteq; print('ok')"
 ```
 
-Explanations for all arguments are provided in main.py and batchASE/scripts/opt_batch.py.
+### 7. Prepare MACE model weights
 
+Ensure `~/.cache/mace/` contains the required weight file (e.g.
+`MACE-OFF23_small.model`). Download from:
 
-### If you want to configure the 7net environment.
+- <https://github.com/ACEsuit/mace-off/tree/main>
+- <https://gitee.com/pfsuo/mace-off/raw/main/mace_off23/MACE-OFF23_small.model>
 
-```sh
-#!/bin/bash
-conda create -n 7net-cueq python=3.10 -y && conda activate 7net-cueq
-cd BOMLIP-CSP/batchASE
-./reproduce/init_7net.sh && source util/env.sh
-```
+### 8. Set up a test run directory
 
-The optimization command for 7net is given in csp.sh
 ```sh
-# Use a fixed batch size for structural optimization
-python "${TOP_DIR}/batchASE/scripts/opt_batch.py" --target_folder "${TAR_DIR}/structures" \
-    --molecule_single 13 --gpu_offset 0 --n_gpus 8 --num_workers 48 --batch_size 2 \
-    --max_steps 3000 --filter1 UnitCellFilter --filter2 UnitCellFilter \
-    --optimizer1 BFGSFusedLS --optimizer2 BFGS --num_threads 2 --cueq true \
-    --use_ordered_files true --model sevennet > opt.log 2>&1
+mkdir run && cp example/* run/
 ```
 
-## Method
-See the BOMLIP-CSP paper for more details.
-
-## License
+### 9. Test crystal structure generation
 
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
-
-### Third-party Dependencies
+```sh
+source .venv/bin activate
+./run/generation.sh
+```
 
-This project includes dependencies with various licenses:
-- **MACE**: MIT License (compatible)
-- **FairChem**: MIT License (compatible)
-- **SevenNet**: GPL v3 License (Note: GPL is a copyleft license)
+### 10. Test crystal structure relaxation
 
-### License Compatibility Notice
+```sh
+source .venv/bin/activate
+./run/relaxation.sh
+```
 
-**Important**: This project can run completely without relying on SevenNet. 
-This project includes SevenNet as an optional dependency, which is licensed under GPL v3.
-If you use SevenNet functionality, you should be aware of the GPL licensing requirements.
-For commercial use or to avoid GPL restrictions, consider using only the MACE calculator 
-functionality.
+## Results & Configuration
 
-## Citation
+- **Results** are written to the `csp_results/` directory.
+- **Configuration files** for generation and relaxation are located in the `run/` directory.
 
-If you use this code in your research, please cite:
+## Tested Environment
 
-```bibtex
-@software{BOMLIP_CSP,
-  author = {Chengxi Zhao, Zhaojia Ma, Dingrui Fan},
-  title = {BOMLIP_CSP: Integrating machine learning interatomic potentials with batched optimization for crystal structure prediction},
-  year = {2025},
-  url = {https://github.com/pic-ai-robotic-chemistry/BOMLIP-CSP}
-}
-```
+Hygon DCU · BW200 · DTK 25.04.1

pyproject.toml

@@ -23,11 +23,11 @@ dependencies = [
 ]
 
 [tool.uv.sources]
-torch = { path = "/data/wangleping/torch-2.5.1+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl" }
+torch = { path = "/data/whl/torch-2.5.1+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl" }
 mace-torch = { path = "./3rdparty/mace", editable = true } 
 cuequivariance-torch = { path = "./3rdparty/cuequivariance_torch/cuequivariance_torch", editable = true }
 fasteq = { path = "./3rdparty/FastEq", editable = true } 
-triton = { path = "../../../../data/wangleping/triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl" }
+triton = { path = "/data/whl/triton-3.0.0+das.opt1.dtk25041-cp310-cp310-manylinux_2_28_x86_64.whl" }
 
 [tool.uv]
 no-build-isolation-package = [