[ggma] Add gyu (ggma yielding utility) tool

Implement gyu CLI tool to automate GGMA model package creation:

- Merge prefill.py and decode.py into unified export.py
- Create modular gpm tool structure:
  - gyu/init.py: Setup venv, install deps (CPU-only torch), clone TICO, extract o2o tools
  - gyu/import.py: Download complete model from HuggingFace
  - gyu/export.py: Run conversion pipeline and create .ggma package
  - gyu/common.py: Shared utilities and constants
  - gyu/clean.py: Remove building directory
  - gyu/gyu: Bash wrapper to dispatch commands

Documentation:
- Rename README.md → DEVELOPER.md (technical guide)
- Add USER.md (user-facing guide)

Author: Sanggyu Lee

…me/ggma/examples/generate_text/README.md …ggma/examples/generate_text/DEVELOPER.mdruntime/ggma/examples/generate_text/README.md renamed to runtime/ggma/examples/generate_text/DEVELOPER.md runtime/ggma/examples/generate_text/README.md renamed to runtime/ggma/examples/generate_text/DEVELOPER.md

@@ -1,6 +1,6 @@
-# TinyLlama Text Generation Example
+# TinyLlama Text Generation Developer Guide
 
-This document provides a step‑by‑step guide for generating and processing a TinyLlama text‑generation model.
+This document provides a detailed technical guide for generating, processing, and optimizing the TinyLlama text-generation model. For basic usage, see [USER.md](USER.md).
 
 ## Summary
 
@@ -12,42 +12,47 @@ This document provides a step‑by‑step guide for generating and processing a
 
 ### 1. Python virtual environment
 ```bash
-cd runtime/ggma/examples/generate_text/
-python3 -m venv _
-source _/bin/activate
+$ cd runtime/ggma/examples/generate_text/
+$ python3 -m venv _
+$ source _/bin/activate
 ```
 
 ### 2. Install required Python packages
 ```bash
-pip install -r requirements.txt
+$ pip install -r tinyllama/tinyllama.requirements
 ```
 
-### 3. Install TICO (Torch IR to Circle ONE)
+### 3. Clone and Install TICO
 ```bash
-# Clone the repository
-git clone https://github.com/Samsung/TICO.git
-# Install it in editable mode
-pip install -e TICO
+$ git clone --depth 1 https://github.com/Samsung/TICO.git
+$ cd TICO
+$ git fetch origin pull/418/head:pr-418
+$ git checkout pr-418
+$ cd ..
+$ pip install -r TICO/requirements.txt
+$ pip install -e TICO --extra-index-url https://download.pytorch.org/whl/cpu
 ```
 
 ### 4. Get [o2o](https://github.com/Samsung/ONE/pull/16233) in PATH
 *Requires the GitHub CLI (`gh`).*
 ```bash
-gh pr checkout 16233
-export PATH=../../../../tools/o2o:$PATH
+$ gh pr checkout 16233
+$ export PATH=../../../../tools/o2o:$PATH
 ```
 
+
+
 ## Generating Model Files
 
 ### 1. Create the prefill and decode Circle model files
 ```bash
-python prefill.py   # Generates prefill.circle
-python decode.py    # Generates decode_.circle
+$ python tinyllama/tinyllama.py --mode prefill   # Generates prefill.circle
+$ python tinyllama/tinyllama.py --mode decode    # Generates decode_.circle
 ```
 
 Verify the generated files:
 ```bash
-ls -lh *.circle
+$ ls -lh *.circle
 # -rw-rw-r-- 1 gyu gyu 18M Nov 14 14:09 decode_.circle
 # -rw-rw-r-- 1 gyu gyu 18M Nov 14 14:09 prefill.circle
 ```
@@ -57,7 +62,7 @@ Fuse attention and normalize KV-cache inputs for the decode model.
 
 ```bash
 # Fuse attention and reshape KV-cache for the decode model
-fuse.attention.py < decode_.circle \
+$ fuse.attention.py < decode_.circle \
     | fuse.bmm_lhs_const.py \
     | reshape.io.py input --by_shape [1,16,30,4] [1,16,32,4] \
     | transpose.io.kvcache.py > decode.circle
@@ -67,14 +72,14 @@ fuse.attention.py < decode_.circle \
 Merge the models, retype input IDs, and clean up.
 
 ```bash
-merge.circles.py prefill.circle decode.circle \
+$ merge.circles.py prefill.circle decode.circle \
     | downcast.input_ids.py \
     | gc.py > model.circle
 ```
 
 Verify final model files:
 ```bash
-ls -l {decode,prefill,model}.circle
+$ ls -l {decode,prefill,model}.circle
 # -rw-rw-r-- 1 gyu gyu 18594868 Nov 22 17:26 decode.circle
 # -rw-rw-r-- 1 gyu gyu 18642052 Nov 22 07:53 prefill.circle
 # -rw-rw-r-- 1 gyu gyu 18629520 Nov 22 17:28 model.circle
@@ -84,19 +89,19 @@ ls -l {decode,prefill,model}.circle
 
 1. Create the package root directory and move `model.circle` there:
 ```bash
-cd runtime/ggma/examples/generate_text
-mkdir tinyllama
-mv model.circle tinyllama/
+$ cd runtime/ggma/examples/generate_text
+$ mkdir tinyllama
+$ mv model.circle tinyllama/
 ```
 
 2. Copy the tokenizer files (replace `{your_snapshot}` with the actual snapshot hash):
 ```bash
-cp -L ~/.cache/huggingface/hub/models--Maykeye--TinyLLama-v0/snapshots/{your_snapshot}/tokenizer.* tinyllama/
-cp -L ~/.cache/huggingface/hub/models--Maykeye--TinyLLama-v0/snapshots/{your_snapshot}/config.json tinyllama/
+$ cp -L ~/.cache/huggingface/hub/models--Maykeye--TinyLLama-v0/snapshots/{your_snapshot}/tokenizer.* tinyllama/
+$ cp -L ~/.cache/huggingface/hub/models--Maykeye--TinyLLama-v0/snapshots/{your_snapshot}/config.json tinyllama/
 ```
 
 ```bash
-tree tinyllama/
+$ tree tinyllama/
 tinyllama/
 ├── model.circle
 ├── tokenizer.json
@@ -106,20 +111,20 @@ tinyllama/
 ## Build and run `ggma_run`
 
 ```bash
-make -j$(nproc)
-make install
+$ make -j$(nproc)
+$ make install
 ```
 
 Check version:
 ```bash
-Product/out/bin/ggma_run --version
-# ggma_run v0.1.0 (nnfw runtime: v1.31.0)
+$ Product/out/bin/ggma_run --version
+ggma_run v0.1.0 (nnfw runtime: v1.31.0)
 ```
 
 Run the model:
 ```bash
-Product/out/bin/ggma_run tinyllama
-# prompt: Lily picked up a flower.
-# generated: { 1100, 7899, 289, 826, 351, 600, 2439, 288, 266, 3653, 31843, 1100, 7899, 289, 1261, 291, 5869, 291, 1261, 31843, 1100, 7899 }
-# detokenized: She liked to play with her friends in the park. She liked to run and jump and run. She liked
+$ Product/out/bin/ggma_run tinyllama
+prompt: Lily picked up a flower.
+generated: { 1100, 7899, 289, 826, 351, 600, 2439, 288, 266, 3653, 31843, 1100, 7899, 289, 1261, 291, 5869, 291, 1261, 31843, 1100, 7899 }
+detokenized: She liked to play with her friends in the park. She liked to run and jump and run. She liked
 ```

runtime/ggma/examples/generate_text/USER.md

@@ -0,0 +1,90 @@
+# TinyLlama Text Generation User Guide
+
+This guide shows how to create a GGMA package for the TinyLlama model using the `gyu` (GGMA Yielding Utility) tool.
+
+## Quick Start
+
+### 1. Initialize environment (one-time setup)
+
+```bash
+$ gyu/gyu init
+```
+
+Python environment (`venv`) and o2o tools are created:
+```bash
+$ ls -ld o2o venv
+drwxrwxr-x 2 gyu gyu 4096 Nov 24 09:44 o2o
+drwxrwxr-x 6 gyu gyu 4096 Nov 24 09:42 venv
+```
+
+> **Note**: The `o2o` directory will be removed once [PR #13689](https://github.com/Samsung/ONE/pull/13689) is merged.
+
+### 2. Import model from HuggingFace
+
+```bash
+$ gyu/gyu import Maykeye/TinyLLama-v0 -r tinyllama/tinyllama.requirements
+```
+
+The HuggingFace model is downloaded to `build/tinyllama-v0/`:
+```
+build
+└── tinyllama-v0
+    ├── backup
+    ├── config.json
+    ├── demo.py
+    ├── generation_config.json
+    ├── model.onnx
+    ├── model.safetensors
+    ├── pytorch_model.bin
+    ├── README.md
+    ├── special_tokens_map.json
+    ├── tokenizer_config.json
+    ├── tokenizer.json
+    ├── tokenizer.model
+    ├── train.ipynb
+    └── valid.py
+```
+
+### 3. Export to GGMA package
+
+```bash
+$ gyu/gyu export -s tinyllama/tinyllama.py -p tinyllama/tinyllama.pipeline
+```
+
+The GGMA package is generated in `build/out/`:
+```
+build/out/
+├── config.json
+├── model.circle
+├── tokenizer.json
+└── tokenizer.model
+```
+
+## Build ggma_run
+
+```bash
+# From ONE root directory
+$ make -j$(nproc)
+$ make install
+```
+
+For detailed build instructions, see the [ONE Runtime Build Guide](https://github.com/Samsung/ONE/blob/master/docs/runtime/README.md).
+
+Confirm that `ggma_run` is built and show its version:
+```bash
+$ Product/out/bin/ggma_run --version
+ggma_run v0.1.0 (nnfw runtime: v1.31.0)
+```
+
+Execute the GGMA package (default prompt) to see a sample output:
+```bash
+$ Product/out/bin/ggma_run build/out
+prompt: Lily picked up a flower.
+generated: { 1100, 7899, 289, 826, 351, 600, 2439, 288, 266, 3653, 31843, 1100, 7899, 289, 1261, 291, 5869, 291, 1261, 31843, 1100, 7899 }
+detokenized: She liked to play with her friends in the park. She liked to run and jump and run. She liked
+```
+
+For detailed run instructions, see the [ggma_run guide](https://github.com/Samsung/ONE/blob/master/runtime/tests/tools/ggma_run/README.md).
+
+
+For developers who want to understand what happens under the hood, see [DEVELOPER.md](DEVELOPER.md).

runtime/ggma/examples/generate_text/decode.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+import shutil
+import os
+
+import argparse
+from common import VENV_DIR
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Clean build artifacts")
+    parser.add_argument("--all",
+                        action="store_true",
+                        help="Remove all generated files including venv, TICO, and o2o")
+    args = parser.parse_args()
+
+    # Always remove build directory
+    build_dir = "build"
+    if os.path.exists(build_dir):
+        print(f"Removing {build_dir} directory...")
+        shutil.rmtree(build_dir)
+    else:
+        print(f"{build_dir} directory does not exist.")
+
+    if args.all:
+        dirs_to_remove = ["TICO", "o2o", VENV_DIR]
+        for d in dirs_to_remove:
+            if os.path.exists(d):
+                print(f"Removing {d} directory...")
+                shutil.rmtree(d)
+        print("Full clean complete.")
+    else:
+        print("Clean complete.")
+
+
+if __name__ == "__main__":
+    main()

runtime/ggma/examples/generate_text/gyu/clean.py

@@ -0,0 +1,12 @@
+import subprocess
+
+# Constants
+VENV_DIR = "venv"
+PR_WORKTREE = "_pr_16233"
+PR_BRANCH = "pr-16233"
+PR_REF = "refs/pull/16233/head"
+
+
+def run_command(cmd, cwd=None, env=None, check=True):
+    print(f"Running: {cmd}")
+    subprocess.run(cmd, shell=True, cwd=cwd, env=env, check=check)