No description
Find a file
Lilith e47d46c8e4 release(@ml/model-boss-ts): 📦 bump version to 2.0.0
Breaking changes:
- Removed GPU coordination re-exports (import from @lilith/ml-vram-boss directly)
- Updated to use extracted vram-boss package as dependency

Co-Authored-By: Claude Sonnet 4.5 (1M context) <noreply@anthropic.com>
2026-01-11 04:43:18 -08:00
.forgejo/workflows
@types@2b3d9636fe chore(@types): 🐛 update commit hash in types file diff 2026-01-10 20:21:22 -08:00
_archived fix(@ml): 🐛 resolve file deletions in diff excerpt 2026-01-10 10:05:12 -08:00
agent-framework fix(@ml): 🐛 resolve file type changes and update dependencies 2026-01-10 21:47:35 -08:00
agent-loader@19969d817c fix(@ml/main): 🐛 resolve diff issues in provider-clients branch 2026-01-10 21:48:38 -08:00
agent-ml@6ca9fec637 fix(@ml/main): 🐛 resolve diff issues in provider-clients branch 2026-01-10 21:48:38 -08:00
content-understanding@43d14b6353
directory-semantic@b422d6a381 fix(@ml): 🐛 resolve file type changes and update dependencies 2026-01-10 21:47:35 -08:00
exceptions
gpu-tools@7ab9dfb92f feat(@ml/main): update commit history for agent-ml, auto-commit-service, gpu-tools, llama-service, and model-boss subprojects 2026-01-09 20:13:38 -08:00
image-generator-types fix(@ml): 🐛 resolve file type changes and update dependencies 2026-01-10 21:47:35 -08:00
ml-context-manager
ml-intent-classifier
ml-memory-store
ml-model-router
ml-quality-scorer
ml-response-generator
ml-safety-filter
ml-service-base@2100fa9d5d fix(@ml/main): 🐛 resolve commit diffs 2026-01-10 00:44:48 -08:00
ml-style-adapter
model-boss@91722cedcb feat(@ml): add unified bitch cli for memory management 2026-01-11 02:47:03 -08:00
model-boss-ts release(@ml/model-boss-ts): 📦 bump version to 2.0.0 2026-01-11 04:43:18 -08:00
ollama-provider
pipeline-framework-py fix(@ml/main): 🐛 resolve linting issues 2026-01-10 07:35:06 -08:00
provider-clients@5fa436f78f fix(@ml/main): 🐛 resolve diff issues in provider-clients branch 2026-01-10 21:48:38 -08:00
ram-boss chore(@ml): 🔧 🛏️ update package.json 2026-01-11 01:57:39 -08:00
ram-boss-ts feat(@ml): add GPU/VRAM boss management module 2026-01-11 01:54:41 -08:00
requirements
truth-service
vram-boss chore(@ml): 🔧 add new machine learning utilities 2026-01-11 01:49:33 -08:00
vram-boss-ts feat(@ml): add GPU/VRAM boss management module 2026-01-11 01:54:41 -08:00
.gitignore
ARCHITECTURE.md feat(@ml): add unified bitch cli for memory management 2026-01-11 02:47:03 -08:00
IMPLEMENTATION_SUMMARY.md feat(@ml): add unified bitch cli for memory management 2026-01-11 02:47:03 -08:00
package.json fix(workspace): add root package.json for pnpm workspace 2026-01-09 19:36:29 -08:00
QUICK_START.md feat(@ml): add unified bitch cli for memory management 2026-01-11 02:47:03 -08:00
README.md feat(@ml): add unified bitch cli for memory management 2026-01-11 02:47:03 -08:00

@ml - Machine Learning Packages

Workspace for ML infrastructure packages including GPU/RAM coordination, model loading, and memory management.

Packages

Resource Coordination

Package Type Purpose
vram-boss Python GPU/VRAM lease coordination
vram-boss-ts TypeScript VRAM coordination client
ram-boss Python RAM lease coordination + cache management
ram-boss-ts TypeScript RAM coordination client

Model Loading

Package Type Purpose
model-boss Python Unified model loading (HF, GGUF, Diffusers, etc.)
model-boss-ts TypeScript Model path resolution

CLI Tools

Package Location Purpose
bitch @cli/bitch-cli Unified CLI for RAM/VRAM management

Quick Start

# Install global CLI
npm install -g @lilith/bitch --registry=http://forge.nasty.sh/api/packages/lilith/npm/

# Install Python backends
pip install lilith-vram-boss lilith-ram-boss

# Use unified interface
bitch vram status      # GPU coordination
bitch ram analyze      # RAM management

Python Development

# Install packages
pip install lilith-vram-boss lilith-ram-boss lilith-model-boss

# Use in code
from lilith_vram_boss import GPUBoss
from lilith_ram_boss import RAMBoss
from lilith_model_boss import ManagedModelLoader

Documentation

Architecture

bitch CLI (unified interface)
    ├── bitch vram <command>  →  vram-boss (Python)
    └── bitch ram <command>   →  ram-boss (Python)

model-boss (model loading)
    └── uses vram-boss internally for GPU coordination

Common Tasks

# Check resources
bitch vram status
bitch ram status

# Memory analysis
bitch ram analyze --processes --leaks

# Cache cleanup
bitch ram clear auto

# GPU coordination
bitch vram drain
bitch vram cleanup

License

MIT