https://www.notion.so/ml-infra/mega-base-cache-24291d247273805b8e20fe26677b7b0f
# B10 TCache
PyTorch compilation cache for Baseten deployments.
## Usage
```python
import b10_tcache
# Inside model.load() function
def load()
# Load cache before torch.compile()
cache_loaded = b10_tcache.load_compile_cache()
# ...
# Your model compilation
model = torch.compile(model)
# Warm up the model with dummy prompts, and arguments that would be typically used in your requests (e.g resolutions)
dummy_input = "What is the capital of France?"
model(dummy_input)
# ...
# Save cache after compilation
if not cache_loaded:
b10_tcache.save_compile_cache()
```
## Configuration
Configure via environment variables:
```bash
# Cache directories
export TORCH_CACHE_DIR="/tmp/torchinductor_root" # Default
export B10FS_CACHE_DIR="/cache/model/compile_cache" # Default
export LOCAL_WORK_DIR="/app" # Default
# Cache limits
export MAX_CACHE_SIZE_MB="1024" # 1GB default
```
## How It Works
### Environment-Specific Caching
The library automatically creates unique cache keys based on your environment:
```
torch-2.1.0_cuda-12.1_cc-8.6_triton-2.1.0 → cache_a1b2c3d4e5f6.latest.tar.gz
torch-2.0.1_cuda-11.8_cc-7.5_triton-2.0.1 → cache_x9y8z7w6v5u4.latest.tar.gz
torch-2.1.0_cpu_triton-none → cache_m1n2o3p4q5r6.latest.tar.gz
```
**Components used:**
- **PyTorch version** (e.g., `torch-2.1.0`)
- **CUDA version** (e.g., `cuda-12.1` or `cpu`)
- **GPU compute capability** (e.g., `cc-8.6` for A100)
- **Triton version** (e.g., `triton-2.1.0` or `triton-none`)
### Cache Workflow
1. **Load Phase** (startup): Generate environment key, check for matching cache in B10FS, extract to local directory
2. **Save Phase** (after compilation): Create archive, atomic copy to B10FS with environment-specific filename
### Lock-Free Race Prevention
Uses journal pattern with atomic filesystem operations for parallel-safe cache saves.
## API Reference
### Functions
- `load_compile_cache() -> bool`: Load cache from B10FS for current environment
- `save_compile_cache() -> bool`: Save cache to B10FS with environment-specific filename
- `clear_local_cache() -> bool`: Clear local cache directory
- `get_cache_info() -> Dict[str, Any]`: Get cache status information for current environment
- `list_available_caches() -> Dict[str, Any]`: List all cache files with environment details
### Exceptions
- `CacheError`: Base exception for cache operations
- `CacheValidationError`: Path validation or compatibility check failed
## Performance Impact
### Debugging
Enable debug logging:
```python
import logging
logging.getLogger('b10_tcache').setLevel(logging.DEBUG)
```
Raw data
{
"_id": null,
"home_page": null,
"name": "baseten-tcache",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "pytorch, torch.compile, cache, machine-learning, inference",
"author": "Shounak Ray",
"author_email": "shounak@baseten.co",
"download_url": "https://files.pythonhosted.org/packages/0d/5b/4fbdce8b4eb90541d9d06e145c3f4f74b5195a445f1dd7cc0af1934b6d3a/baseten_tcache-0.0.1.tar.gz",
"platform": null,
"description": "https://www.notion.so/ml-infra/mega-base-cache-24291d247273805b8e20fe26677b7b0f\n\n# B10 TCache\n\nPyTorch compilation cache for Baseten deployments.\n\n## Usage\n\n```python\nimport b10_tcache\n\n# Inside model.load() function\ndef load()\n # Load cache before torch.compile()\n cache_loaded = b10_tcache.load_compile_cache()\n\n # ...\n\n # Your model compilation\n model = torch.compile(model)\n # Warm up the model with dummy prompts, and arguments that would be typically used in your requests (e.g resolutions)\n dummy_input = \"What is the capital of France?\"\n model(dummy_input)\n\n # ...\n\n # Save cache after compilation\n if not cache_loaded:\n b10_tcache.save_compile_cache()\n```\n\n## Configuration\n\nConfigure via environment variables:\n\n```bash\n# Cache directories\nexport TORCH_CACHE_DIR=\"/tmp/torchinductor_root\" # Default\nexport B10FS_CACHE_DIR=\"/cache/model/compile_cache\" # Default \nexport LOCAL_WORK_DIR=\"/app\" # Default\n\n# Cache limits\nexport MAX_CACHE_SIZE_MB=\"1024\" # 1GB default\n```\n\n## How It Works\n\n### Environment-Specific Caching\n\nThe library automatically creates unique cache keys based on your environment:\n\n```\ntorch-2.1.0_cuda-12.1_cc-8.6_triton-2.1.0 \u2192 cache_a1b2c3d4e5f6.latest.tar.gz\ntorch-2.0.1_cuda-11.8_cc-7.5_triton-2.0.1 \u2192 cache_x9y8z7w6v5u4.latest.tar.gz\ntorch-2.1.0_cpu_triton-none \u2192 cache_m1n2o3p4q5r6.latest.tar.gz\n```\n\n**Components used:**\n- **PyTorch version** (e.g., `torch-2.1.0`)\n- **CUDA version** (e.g., `cuda-12.1` or `cpu`)\n- **GPU compute capability** (e.g., `cc-8.6` for A100)\n- **Triton version** (e.g., `triton-2.1.0` or `triton-none`)\n\n### Cache Workflow\n\n1. **Load Phase** (startup): Generate environment key, check for matching cache in B10FS, extract to local directory\n2. **Save Phase** (after compilation): Create archive, atomic copy to B10FS with environment-specific filename\n\n### Lock-Free Race Prevention \n\nUses journal pattern with atomic filesystem operations for parallel-safe cache saves.\n\n## API Reference\n\n### Functions\n\n- `load_compile_cache() -> bool`: Load cache from B10FS for current environment\n- `save_compile_cache() -> bool`: Save cache to B10FS with environment-specific filename\n- `clear_local_cache() -> bool`: Clear local cache directory\n- `get_cache_info() -> Dict[str, Any]`: Get cache status information for current environment\n- `list_available_caches() -> Dict[str, Any]`: List all cache files with environment details\n\n### Exceptions\n\n- `CacheError`: Base exception for cache operations\n- `CacheValidationError`: Path validation or compatibility check failed\n\n## Performance Impact\n\n### Debugging\n\nEnable debug logging:\n\n```python\nimport logging\nlogging.getLogger('b10_tcache').setLevel(logging.DEBUG)\n```\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Distributed PyTorch compilation cache for Baseten - Environment-aware, lock-free compilation cache management",
"version": "0.0.1",
"project_urls": {
"Documentation": "https://docs.baseten.co/development/model/b10-tcache",
"Homepage": "https://docs.baseten.co/development/model/b10-tcache",
"Repository": "https://pypi.org/project/b10-tcache/"
},
"split_keywords": [
"pytorch",
" torch.compile",
" cache",
" machine-learning",
" inference"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "a782034d884c9af47d663386316943d539176147d7c579cc34d9e07dccb427f9",
"md5": "5f82e90f883f9d1fc9c218358e542d42",
"sha256": "e2825267f234717fbef109a1c7de956fed7654c1934674aae7aac27efe034cfa"
},
"downloads": -1,
"filename": "baseten_tcache-0.0.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5f82e90f883f9d1fc9c218358e542d42",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 8341,
"upload_time": "2025-08-11T18:53:17",
"upload_time_iso_8601": "2025-08-11T18:53:17.688367Z",
"url": "https://files.pythonhosted.org/packages/a7/82/034d884c9af47d663386316943d539176147d7c579cc34d9e07dccb427f9/baseten_tcache-0.0.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "0d5b4fbdce8b4eb90541d9d06e145c3f4f74b5195a445f1dd7cc0af1934b6d3a",
"md5": "124cfe35205d6359f5daa6bb540ffcff",
"sha256": "84fff1e31ec64ee119f8ed8edb6733c32cbac27db7432fc7e76e519741af0dc0"
},
"downloads": -1,
"filename": "baseten_tcache-0.0.1.tar.gz",
"has_sig": false,
"md5_digest": "124cfe35205d6359f5daa6bb540ffcff",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 6220,
"upload_time": "2025-08-11T18:53:18",
"upload_time_iso_8601": "2025-08-11T18:53:18.934961Z",
"url": "https://files.pythonhosted.org/packages/0d/5b/4fbdce8b4eb90541d9d06e145c3f4f74b5195a445f1dd7cc0af1934b6d3a/baseten_tcache-0.0.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-11 18:53:18",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "baseten-tcache"
}
JSON