mirror of
https://fastgit.cc/github.com/Michael-A-Kuykendall/shimmy
synced 2026-04-21 13:23:05 +08:00
65298f767e
- Add comprehensive MLX engine implementation with Python MLX bindings - Implement MLX model discovery, loading, and native inference pipeline - Add MLX feature flag compilation and Apple Silicon hardware detection - Create dedicated GitHub Actions workflow for MLX testing on macos-14 ARM64 - Add MLX documentation to README and wiki with capability descriptions - Implement pre-commit hooks enforcing cargo fmt, clippy, and test validation - Fix GPU backend tests to properly force specific backends instead of auto-detection - Resolve property test race conditions with serial test execution - Update release workflow validation and platform-specific test expectations - Add MLX implementation plan and cross-compilation toolchain support 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
28 lines
842 B
YAML
28 lines
842 B
YAML
version: '3.8'
|
|
|
|
services:
|
|
shimmy:
|
|
image: ghcr.io/michael-a-kuykendall/shimmy:latest
|
|
container_name: shimmy-server
|
|
ports:
|
|
- "11434:11434" # Shimmy server port
|
|
volumes:
|
|
- ./models:/app/models # Mount your models directory
|
|
- shimmy-cache:/root/.cache # Persistent cache for downloads
|
|
environment:
|
|
- SHIMMY_BASE_GGUF=/app/models # Point to mounted models
|
|
- SHIMMY_PORT=11434 # Server port
|
|
- SHIMMY_HOST=0.0.0.0 # Listen on all interfaces
|
|
restart: unless-stopped
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia # GPU support (optional)
|
|
count: all
|
|
capabilities: [gpu]
|
|
|
|
volumes:
|
|
shimmy-cache:
|
|
driver: local
|