mirror of
https://github.com/cloudstack-llc/mlx-knife.git
synced 2026-07-18 20:54:26 -04:00
The BROKE Cluster Team
fb54f59cd4
Fixes Issue #32 (generic multi-EOS detection) and Issue #37 (model detection) - Generic stop token detection: Multi-EOS models (MXFP4, Qwen, Llama) now use eos_token_ids Set instead of model-specific workarounds - Private/org MLX model detection: `mlxk run` now works outside `mlx-community/*` namespace - Commit-pinned compatibility checks: Models with `@commit_hash` validated before inference - Packaging dependencies: Fixed `pip install -e .` requirements - ADR-009: Stop Token Detection Fix (generic approach + test strategy) - ADR-011: E2E Live Test Architecture (planned) See CHANGELOG.md and TESTING.md for details.
Architecture Decision Records (ADRs)
Overview
This directory contains Architecture Decision Records (ADRs) that document significant architectural and design decisions for the MLX-Knife project.
Active ADRs
| ADR | Title | Status | Date |
|---|---|---|---|
| ADR-001 | JSON API Strategy & 2.0 Migration Path | Accepted | 2025-08-28 |
| ADR-002 | Edge Cases from 1.x Test Suite | Accepted | 2025-08-28 |
| ADR-003 | Server and Run Functionality Port from 1.x to 2.0 | Accepted | 2025-09-10 |
| ADR-004 | Enhanced Error Handling & Logging | Accepted | 2025-10-19 |
| ADR-005 | Clone Implementation Beta3 | Superseded by ADR-007 | 2025-09-18 |
| ADR-006 | Clone Implementation Revised | Superseded by ADR-007 | 2025-09-18 |
| ADR-007 | Clone Implementation Fixed Strategy | Accepted | 2025-09-18 |
| ADR-008 | MLXModel Package Format | Accepted | 2025-10-17 |
| ADR-009 | Stop Token Detection Fix | Accepted | 2025-10-21 |
| ADR-010 | Reasoning Content API | Draft | 2025-10-21 |
| ADR-011 | E2E Live Test Architecture | Accepted | 2025-10-21 |
ADR Format
Each ADR follows this structure:
- Status: Proposed / Accepted / Rejected / Superseded
- Context: Why this decision is needed
- Decision: What we decided to do
- Consequences: What happens as a result