d4cd89fab0
Release 2.0.4 stable - see CHANGELOG.md for details
2026-02-11 15:05:09 +01:00
7f10187bee
fix: Runtime gates + unit tests; benchmark GPU analysis
...
Core:
- Run preflight passes probe/framework to audio_runtime_compatibility
- STT model_type gate extended (vibevoice, audio)
- MLX 0.30.x compat: catch Exception in whisper_tokenizer
- Embedding-gate unit tests (3 tests)
- Removed get_encoding duplication (-45 LOC)
Benchmark:
- GPU analysis section in reports
2026-02-07 23:38:34 +01:00
e021fb32cd
Release 2.0.4-beta.10: Audio PyPI fix (tiktoken workaround complete)
...
Audio/Whisper works with pip install - no Git workaround needed.
See CHANGELOG.md for details.
Tested: 647 passed, 11 skipped (Python 3.10-3.12)
2026-02-05 10:42:50 +01:00
69a3c19c16
Release 2.0.4-beta.9: PyPI-ready with tiktoken workaround
...
Changes:
- Bundle tiktoken assets locally (mlxk2/assets/whisper/*.tiktoken)
- Monkey-patch mlx-audio to use bundled assets at import time
- Update pyproject.toml: mlx-audio>=0.3.1 from PyPI (no Git install)
- Simplify README: 3 clear installation methods
- Add NOTICE file for tiktoken asset attribution
Fixes: mlx-audio Issue #479 (missing tiktoken assets in PyPI wheels)
Workaround: Temporary until upstream fix available
2026-02-04 14:41:52 +01:00
bf7480d042
Release 2.0.4-beta.9: Audio transcription via mlx-audio
...
Major Features:
- Audio transcription via mlx-audio backend (Whisper, >10min duration)
- OpenAI /v1/audio/transcriptions endpoint
- Memory Gate System (Vision: 8GB, Audio: 4GB)
- Config-based backend routing (ADR-020)
- Benchmark toolchain (memmon/memplot, Schema v0.2.2)
Key Fixes:
- EuroLLM tokenizer decoding
- Vision-model text-only routing regression
- Multimodal model context length detection
- Memory cleanup bug (mx.metal.clear_cache)
- Orphan process bug
Test Results:
- Unit tests: 647 passed, 11 skipped (Python 3.10-3.12)
- wet-umbrella: 171 passed total
See CHANGELOG.md for complete details and known issues.
2026-02-04 03:10:30 +01:00
e8b10ea10b
Release 2.0.4-beta.8: Audio transcription support (experimental)
...
Audio input via --audio flag (CLI) and input_audio content type (Server API).
Uses mlx-vlm native audio processing. ~30s duration limit (model constraint).
Currently only Gemma-3n tested (requires --repair-index fix).
Also includes:
- SERVER-HANDBOOK compliance (image limits, validation error envelopes)
- Dependency updates: mlx>=0.30.0, mlx-lm>=0.30.0, huggingface-hub>=1.0.0
- Audio E2E test suite + ADR-019
2026-01-23 20:20:59 +01:00
5751545b8b
Release 2.0.4-beta.7: Server robustness + Vision per-chunk streaming
...
- Server: exit codes, /v1/models crash fix, vision routing, MLXK2_MAX_TOKENS
- Vision: true SSE streaming, hallucination fix (local numbering)
- Workspace: list prefix-match, push ambiguous pattern handling
- Docs: SERVER-HANDBOOK accuracy updates
See CHANGELOG.md for details.
2026-01-18 16:57:32 +01:00
53d9cca82d
Release 2.0.4-beta.6: Local workspace workflow + Vision batch processing
...
- Complete local development cycle: clone → repair → run/show/server on
workspace paths without HuggingFace round-trips
- Vision processing now defaults to safe chunking (one image at a time,
prevents OOM + hallucination)
- Resumable clone with --force-resume and deterministic temp cache naming
- Improved test infrastructure (umbrella marker convention)
- 161 Wet Umbrella tests passing including new Vision→Geo pipe integration tests
See CHANGELOG.md for complete details.
2026-01-07 17:11:07 +01:00
25609e4dcb
Release 2.0.4-beta.5: Community repair tool + OS-agnostic benchmarking
...
Closes #49 (Mistral Tokenizer Bug)
Major features:
- Workspace Infrastructure (ADR-018 Phase 0a): Managed workspace detection,
provenance metadata, backward compatible with unmanaged workspaces
- Convert Operation (ADR-018 Phase 1): `mlxk convert --repair-index` fixes
mlx-vlm #624 affected models (7+ models including Qwen2.5-VL, gemma-3)
- Resumable Pull: Auto-detect partial downloads with `--force-resume`
- Wet Umbrella Test Integration: Single entry point for all real model tests
Fixes:
- #49 : BPE space markers now correctly converted (Mistral-family models)
- Vision Portfolio Discovery: Filter by capabilities instead of model_type
- Memory Cleanup Hook: Triggers for both live_e2e and wet markers
Test suite: 528 passed, 60 skipped (Python 3.9-3.14)
2025-12-31 16:05:18 +01:00
c51ca1b10e
Release 2.0.4-beta.4: Pixtral pad_token fix (mlx-vlm upstream)
...
Fixed Pixtral text-only regression via upstream mlx-vlm fix.
Updated dependency to Blaizzy/mlx-vlm@c536165d (merged PR #643 ).
Will switch to PyPI v0.3.10 when released.
Test suite: 144 passed, 21 skipped.
2025-12-25 20:17:51 +01:00
d3f7d091bc
Release 2.0.4-beta.3: Dependency compatibility + Documentation
...
Bugfixes and compatibility improvements. No new features.
Core fixes:
- Framework detection for web API models (Issue #48 )
- Video-only model filtering from vision capability
- Page size detection for memory metrics (macOS)
- Model switch log timing (after load completion)
Compatibility:
- hub 1.x + transformers 5.0 support
- Python 3.9-3.14 verified (494 tests passing)
Testing infrastructure:
- Benchmark schema v0.2.0 (hardware profiling, system health)
- Benchmark template v1.0 (automated JSONL→Markdown reports)
- Memory timeline visualization (memplot.py)
- Unified model filter (build_model_object single source)
Documentation:
- Multi-Modal Support section in README (Vision subsection)
- JSON API 0.1.5-0.1.6 marked Stable
- Vision promoted from alpha to beta status
- Removed conceptual drift and outdated references
See CHANGELOG.md for complete details.
2025-12-23 12:19:04 +01:00
f9e40c1720
Release 2.0.4-beta.2: PyPI compatibility + improved documentation
...
- Fix: Use PyPI mlx-vlm>=0.3.9 instead of Git URL (PyPI requirement)
- Doc: Add Vision installation instructions to README Installation section
- Doc: Clarify Python version requirements (Text: 3.9-3.14, Vision: 3.10-3.14)
- Doc: Update all version references (2.0.4-beta.1 → 2.0.4-beta.2)
- Version: 2.0.4b1 → 2.0.4b2
2025-12-16 21:10:16 +01:00
86f669dc82
Release 2.0.4-beta.1: Vision + Pipes + Memory
...
- Vision Support (Issue #45 ): CLI + Server with OpenAI-compatible image API, EXIF metadata
- Unix Pipes (ADR-014): stdin support, isatty detection, SIGPIPE handling
- Memory-Aware Loading (ADR-016): Pre-load checks with >70% RAM warnings
- Python 3.9-3.14: Full compatibility verified (476-485 tests passing)
- Fixed: --log-json regression (Issue #44 ), Vision multimodal history filtering
See CHANGELOG.md for complete details.
2025-12-16 19:35:30 +01:00
05f1c30486
Release 2.0.3: Foundation for pipes
...
Foundation release for Unix pipe integration with stderr separation,
benchmark infrastructure, and reasoning control improvements.
Breaking Changes:
- stdout/stderr separation (Issue #43 ) - errors to stderr in human mode
- JSON mode unchanged (all output to stdout)
Features:
- Benchmark reporting infrastructure (ADR-013 Phase 0)
- --no-reasoning flag (Issue #40 partial - GPT-OSS/QwQ only)
- Interactive mode reasoning control (review_report.md fixes)
Bug Fixes:
- huggingface-hub 1.x incompatibility (critical dependency fix)
- Streaming parity tests refactored (Portfolio Discovery)
Testing:
- 308 tests passing (Python 3.9-3.13)
- 35 skipped (opt-in live tests)
- 79/91 E2E tests passing with HF_HOME
See CHANGELOG.md for complete details and migration guide.
2025-11-17 22:54:06 +01:00
d32d3185dd
Release 2.0.2: Test infrastructure hardening & empirical validation
...
Stable release completing Issue #32 recovery plan - all tests passing.
Bug Fixes:
- Test collection regression (E2E suite parametrization)
- Stop token ordering (batch + streaming modes)
- E2E test temperature flakiness (deterministic sampling)
- Web API framework detection (PR #42 by @limey, fixes #41 )
- E2E test marker fix (show_model_portfolio diagnostics)
Architecture:
- mlx-lm API evaluation: Keep manual text-based implementation
- Stop token workarounds: All 3 validated (Phi-3, DeepSeek-R1, GPT-oss)
Testing:
- Portfolio Discovery: 73/81 tests, 17 models, 0 failures
- E2E infrastructure hardened (TOKENIZERS, polling, gc.collect())
- Multi-Python validation: 3.9-3.13 passing
Documentation:
- ADR-009 Outstanding Work completed + Implementation Plan removed
- TESTING-DETAILS.md: Portfolio Discovery + E2E Architecture updated
- CHANGELOG.md: Complete 2.0.2 stable release notes
2025-11-15 22:10:08 +01:00
21cf188fcc
Release 2.0.1: Portfolio Discovery + CLI Exit Code Fixes
...
Issue #32 : Stop token Portfolio Discovery validates generic fix across all models
- Auto-discovers MLX chat models in HF_HOME with 4-filter validation
- RAM-aware testing (40-70% budgets) prevents OOM
- Empirical report generation (stop_token_config_report.json)
- Fallback to 3 predefined models without HF_HOME
- Implementation: tests_2.0/test_stop_tokens_live.py (~110 LOC)
Issue #38 : CLI exit codes now propagate run command errors correctly
- Both text and JSON modes return exit code 1 on model execution failures
- Fixed: run_model() now returns error strings in both modes
- Implementation: mlxk2/operations/run.py + mlxk2/cli.py error detection
- New tests: tests_2.0/test_cli_run_exit_codes.py (9 comprehensive tests)
Testing: 306 passed, 20 skipped (zero regressions)
Docs: Updated README, TESTING, SECURITY for 2.0.1 stable release
Version: 2.0.0 → 2.0.1 (mlxk2/__init__.py)
2025-11-08 20:28:54 +01:00
a2ca3da2d9
Release 2.0.0: Full rewrite with Apache 2.0 license
...
MLX Knife 2.0 replaces 1.x as the primary version.
Highlights:
- Full 1.x feature parity (list, show, pull, rm, run, server, health)
- JSON API for automation (--json flag)
- Enhanced error handling and logging
- Runtime compatibility checks
- Improved stop token detection
- License: MIT→Apache 2.0
Breaking changes:
- mlxk rm: requires --force flag for models with active locks
Migration guide: MIGRATION.md
Changelog: CHANGELOG.md
Testing: 297/317 tests passed, Python 3.9-3.13 verified
Merge branch 'feature/2.0.0-alpha.1'
2025-11-06 16:00:35 +01:00
ae80bbe554
Release 2.0.0: Package rename, Apache 2.0 license, documentation updates
2025-11-06 15:21:10 +01:00
fb54f59cd4
Release 2.0.0-beta.6: Stop token & compatibility bug fixes
...
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.
2025-10-24 15:46:42 +02:00
f5fe1dd061
Release 2.0.0-beta.5: Enhanced error handling & bug fixes
...
Features:
- Enhanced error handling & logging (ADR-004): Unified error envelope, structured logging with JSON support, request correlation
- Legacy format detection (Issue #37 ): Runtime compatibility check for weight file formats
Bug Fixes:
- Issue #37 : Models with legacy weight formats now correctly detected as runtime-incompatible
- CLI regression fix: mlxk2 without arguments shows help instead of JSON error
Test Status: 295/295 passed, 14 skipped
2025-10-21 00:24:47 +02:00
4b75a22726
Release 2.0.0-beta.4: Runtime compatibility check (Issue #36 )
...
- JSON API 0.1.5: runtime_compatible + reason fields
- mlx-lm dependency updated to >=0.28.3 (stable PyPI release)
- Human output: healthy / healthy* / unhealthy status display
- All tests passing (253 passed, 12 skipped) across Python 3.9-3.13
2025-10-18 16:06:58 +02:00
d07bf66990
minor changes of badges
2025-10-01 12:09:22 +02:00
58facfb079
markdown formatting issues in README.md corrected
2025-10-01 11:47:45 +02:00
316c2f5585
README: Add beta release installation instructions
...
- Add recommended beta installation section with direct GitHub release URL
- Simplifies user onboarding for v2.0.0-beta.3 testing
- Reorganized Quick Start with clear Development vs Release paths
2025-09-21 13:59:00 +02:00
4a8bcba9b4
Update README.md: linked to updated gif Demo
2025-09-18 14:19:27 +02:00
9261bc0c4e
2.0.0-beta.3: Feature Complete - Clone Implementation & Issue Resolution
...
- Clone Feature (Issue #29 ): Complete workspace-based workflow with ADR-007
- Pull Preflight (Issue #30 ): Prevents cache pollution from gated/private repos
- Lenient MLX Detection (Issue #31 ): Framework detection beyond mlx-community
- Multi-shard Health (Issue #27 ): Strict completeness validation
- Full JSON API 0.1.4: Complete schema for all 10 commands
- Test Suite: 254/254 passed, comprehensive validation
See CHANGELOG.md fnd TESTING.md or technical implementation details.
2025-09-18 14:09:32 +02:00
6279b82be8
Release: MLX Knife 1.1.1 - Stable Release
...
Promote 1.1.1-beta.3 to stable with metadata updates:
✅ Version: 1.1.1b3 → 1.1.1 (stable)
✅ PyPI classifier: Development Status 4 Beta → 5 Stable
✅ Documentation: Updated to reflect stable release
✅ Sponsor link: Fixed tileslauncher → tileshq
✅ Security policy: Support 1.1.1 + 2.0.0-beta.3 only
No functional changes - same MXFP4 + GPT-OSS features as beta.3
2025-09-14 18:52:25 +02:00
57bf6d86be
2.0.0-beta.3: Feature Complete - Full 1.1.1 Parity Achieved
...
Major Features Added:
• Complete run command implementation with interactive/single-shot modes
• MLXRunner core engine ported from 1.x with modular architecture
• OpenAI-compatible server with SIGINT-robust supervisor mode
• Experimental push feature properly isolated behind environment variable
Key Improvements:
- Full feature parity with 1.1.1 stable releases
- Enhanced human output formatting across all commands
- Clean separation of stable (184 tests) vs experimental features
- Updated demo GIF showcasing improved 2.0 interface
Fixes:
- Pull operation cache pollution (Issue #30 ) with preflight access checks
- Test stability improvements across all environments
Architecture:
- Modular runner design with focused helper modules
- Thread-safe model loading and memory management
- stable testing across Python 3.9-3.13
Ready for use as comprehensive 1.x alternative.
2025-09-14 18:04:18 +02:00
ce46601d9d
Release: 1.1.1-beta.3 - MXFP4 support and GPT-OSS reasoning
...
• MXFP4 Quantization Support (MLX ≥0.29.0, MLX-LM ≥0.27.0)
• GPT-OSS Reasoning Models with --hide-reasoning flag
• Enhanced Show Command with improved quantization display
• Documentation updates (README.md, TESTING.md)
See CHANGELOG.md for complete technical details.
Partial Issue #32 (GPT-OSS only, other reasoning models remain open).
2025-09-10 13:32:04 +02:00
3f57248121
2.0.0-alpha.3: lenient MLX detection + push branch handling
...
- Detect MLX/chat via README front‑matter + tokenizer; unify list/show; human list filters aligned (Refs #31 )
- Push: create missing branch with --create and retry once on “Invalid rev id”; tolerate missing branches
offline; no‑op still creates branch with --create
- Tests: add offline retry test; detection/human coverage; live list (opt‑in); 98/98 passing
- Docs/Meta: CHANGELOG/TESTING/README/SECURITY/CLAUDE updated; hard split 1.x from this branch; Apache‑2.0 + NOTICE
2025-09-08 01:14:01 +02:00
5045f9e1bd
Release: 1.1.1‑b2 — Issue #31 , stable server tests
...
- Lenient MLX detection via README/tokenizer (Issue #31 )
- CLI: `show` type, strict `list` (chat), `run` accepts private MLX
- Server tests: RAM‑aware gating with `mlxk show`, MoE parsing fix (8x7B), server‑manager process guard, thread‑based timeout
- Multi‑Python script hardened; no ANSI; log tail on errors
- Docs: CHANGELOG, TESTING, CLAUDE updated; 166/166 green (Py 3.9–3.13), 32 server tests green
2025-09-07 02:24:08 +02:00
eedb91b75c
Feat: add experimental push (2.0.0-alpha.2)
...
- Push (upload-only): quiet JSON by default; capture hub logs in data.hf_logs
- No-op detection aligned to hub signal; clear commit fields; uploaded_files_count=0
- Add --dry-run (plan vs remote) and --check-only (offline preflight); merge .hfignore; extend
default ignores
- Human output: concise; --verbose shows commit URL; JSON shape unchanged
- Tests: add offline dry-run cases; live push remains opt-in (wet/live_push)
- Docs: README push section updated; TESTING.md reference + mini-matrix;
- Changelog: add 2.0.0-alpha.2; note Issue #31 under 1.1.1 pending
- Spec: keep schema stable (0.1.3); CLI/version docs consistent
2025-09-05 22:42:39 +02:00
b9db12ae89
Fix: strict multi-shard health checks ( #27 ) — backport to 1.x; bump 1.1.1b1
...
Summary
- Backports the 2.0 strict health policy to 1.x and ships as a pre-release.
Health changes (cache_utils.py)
- Index-aware: validate safetensors and PyTorch indexes; all referenced shards must exist, be >0B, and not be Git LFS
pointers.
- Pattern policy: shard patterns (model-XXXXX-of-YYYYY.*) without an index → unhealthy (parity with 2.0).
- Partial/tmp markers: any “.partial”, “.tmp”, or names containing “partial” anywhere under the snapshot → unhealthy.
- LFS scan: recursive detection of Git LFS pointer files (<200B with LFS header).
- Single-file fallback: non-empty .safetensors/.bin/*.gguf (no pattern shards) remain healthy.
- Ergonomics: is_model_healthy() accepts direct snapshot paths; check_lfs_corruption() scans recursively.
Tests
- Add tests/unit/test_health_multishard.py covering:
- index complete → healthy; missing/empty shard → unhealthy; LFS pointer → unhealthy
- pattern shards (no index) → unhealthy
- partial marker → unhealthy
- PyTorch index parity (complete → healthy)
- single-file safetensors/gguf → healthy
Docs
- CHANGELOG.md: add 1.1.1-beta.1 with detailed rules; note GitHub tag vs PyPI mapping (1.1.1-beta.1 ↔ 1.1.1b1).
- README.md: tests badge 160/160; pre-release note for 1.1.1b1.
- TESTING.md: status 160/160; update test structure (add test_health_multishard.py; remove 2.0 note).
Version
- version = 1.1.1b1 (PEP 440 pre-release); VERSION = (1, 1, 1).
Behavioral impact
- Health reporting is stricter (cannot regress functionality): incomplete multi-shard downloads correctly report
unhealthy. No changes to pull/run/server behavior.
Validation
- Python 3.9 local: 160 passed, 36 deselected; warnings eliminated on 3.9/3.10 under project defaults.
- New multishard tests pass; manual spot-checks show expected unhealthy→healthy transitions as downloads complete.
Release
- GitHub: tag v1.1.1-beta.1 (Pre-release).
- PyPI: upload 1.1.1b1 (install via pip install --pre mlx-knife).
2025-09-01 01:26:27 +02:00
19a66674c0
2.0.0-alpha.1: human output default; strict health ( #27 , PyTorch index)
...
See CHANGELOG.md and README.md
2025-08-31 22:25:43 +02:00
f511dd9c74
Docs: add sponsor section + badge; add FUNDING; fix footer to 1.1.0
2025-08-29 19:58:32 +02:00
de7ccf9018
2.0.0-alpha: default 2.0 tests, cache safety, and docs
...
Testing:
- pytest defaults to tests_2.0 via pytest.ini
- README/TESTING updated; Quick Start uses `pip install -e . && pip install pytest`
Safety:
- Add test-cache sentinel + centralized checks
- Strict delete guard via MLXK2_STRICT_TEST_DELETE=1
- Hide sentinel from 2.0 list output
Portability:
- Remove site-specific paths; generic test/user cache detection (mlxk2_test_ prefix + sentinel)
Docs:
- Environment & Caches, HF cache integrity
- Local-only hooks/excludes and local test script (excluded from VCS)
2025-08-29 16:57:45 +02:00
d375e1bd3e
MLX-Knife 2.0.0-alpha: Issue #27 Discovery & Development README
...
Major Achievements:
- Live reproduction and documentation of Issue #27 (health check false positive)
- Comprehensive development README.md for alpha phase parallel usage
- JSON API specification integration and references
- 45/45 tests passing with production-quality reliability
Issue #27 Critical Discovery:
- Health check false positives for multi-part model downloads
- Root cause: Multi-part pattern detection flaw in shared logic
- GitHub issue created with reproduction steps and technical analysis
2.0.0-Alpha Development Status:
- Revolutionary test isolation architecture complete
- Atomic cache system with triple safety verification
- Development handbook with parallel deployment guide
- Ready for production testing and broke-cluster integration
2025-08-28 23:49:14 +02:00
cf169e28ad
Release MLX Knife 1.1.0 - Stable Release
...
Complete isolated test system with 150/150 tests passing.
Production-ready after successful beta testing cycle.
See CHANGELOG.md for comprehensive details including:
- All critical issues from 1.1.0-beta3 resolved
- Enhanced test infrastructure with real model validation
- Multi-Python compatibility (3.9-3.13)
2025-08-26 16:30:12 +02:00
7d0d6be66d
Release MLX Knife 1.1.0-beta3 - Critical Cache Management Fixes
...
Three major bug fixes for production readiness:
- Issue #21 : Fix crash on fresh installations (empty cache directory)
- Issue #22 : Suppress urllib3 LibreSSL warnings on macOS Python 3.9
- Issue #23 : Fix double rm execution bug - models now deleted in single command
Test improvements:
- 140/140 tests passing (up from 137)
- Added real integration tests for lock cleanup
- Fixed unit tests broken by path corrections
All known cache management issues resolved for stable release.
2025-08-26 01:46:40 +02:00
1aad374d08
Release MLX Knife 1.1.0-beta2 - Critical Bug Fixes & Test Stability
...
Major fixes:
- Issue #19 : Server response truncation resolved - large context models work at full capacity
- Issue #20 : End-Token filtering in non-streaming mode - clean professional output
- Test stability: Fixed flaky server tests, improved lifecycle management
Technical changes:
- Server: Dynamic token limits by default (--max-tokens None)
- MLXRunner: Added _filter_end_tokens_from_response() for batch consistency
- Tests: 132/132 passing + 48 comprehensive server tests
- Documentation: Updated CHANGELOG.md, README.md, TESTING.md
2025-08-22 23:16:50 +02:00
74239c4e43
Release MLX Knife 1.1.0-beta1 - Dynamic Token Limits & Enhanced Web Client
...
Issues Resolved:
• Issue #15 : Token limits vs natural stop tokens race condition - FIXED
• Issue #16 : Interactive vs server token limit policies - FIXED
Major Improvements:
• Automatic optimal token limits - no configuration needed
• Manual --max-tokens control still available when desired
• Eliminates old hardcoded 500/2000 token restrictions
• Performance gains: Up to 524x improvement for large context models
• Enhanced web client with model capabilities display and better UX
Additional Enhancements:
• Enhanced /v1/models API with context_length field
• Comprehensive test expansion: 114 → 131 tests (131/131 passing)
• Python 3.9-3.13 compatibility verified
Known Issues (Beta Status):
• Server deadlock possible under extreme concurrent model loading stress
• Workaround: Avoid simultaneous heavy model operations
2025-08-21 17:36:44 +02:00
6117e571ca
Release MLX Knife 1.0.4 - Issue #14 Chat Self-Conversation Fix & Web UI Overhaul
...
Fix Issue #14 : Interactive chat self-conversation bug resolved
- Added context-sensitive chat stop tokens (\nHuman:, \nAssistant:, \nYou:, \nUser:)
- Smart priority system: native model stop tokens first, chat tokens as fallback
- Affects both `mlxk run` and `mlxk server` modes with backward compatibility
Web UI complete transformation (simple_chat.html):
- 🦫 Beaver branding replaces 🔪 knife emoji
- Model and chat history persistence across browser sessions
- Smart model switching with option to keep or clear chat history
Testing infrastructure enhancements:
- Automated server testing with RAM-aware model filtering
- 15 new regression tests across 7+ MLX models validating Issue #14 fix
- Comprehensive TESTING.md guide for server-based testing
All 114 tests passing
2025-08-19 20:43:44 +02:00
1f70b4984a
Release MLX Knife 1.0.3 - GitHub Issues Implementation & Enhanced User Experience
...
Community-driven feature development implementing key GitHub Issues:
- Fix Issue #7 : Health check consistency for fuzzy model names - unified health check logic ensures
identical status regardless of name format (Phi-3 vs mlx-community/Phi-3-mini-4k-instruct-4bit)
- Add Issue #6 : Repository name validation - pre-validation for HuggingFace Hub 96-character limit with
clear error messages
- Add Issue #13 : Hash-based disambiguation - use commit hashes to resolve ambiguous model names (mlxk show
Llama@de2dfaf5 → mlx-community/Llama-3.3-70B-Instruct-4bit)
Enhanced user experience:
- Pure local hash resolution without external API calls, offline-capable
- Improved model name disambiguation logic for better workflow
- Real user workflow support - see hashes in mlxk list, use directly in other commands
2025-08-18 20:21:43 +02:00
cbd25c658d
Release MLX Knife 1.0.2 - HF_HOME Cache Consistency & Corruption Fixes │
...
│ │
│ Major bug fixes addressing cache path inconsistencies and silent failures: │
│ - Fix Issue #11 : HF_HOME environment variable handling - unified cache logic ensures consistent │
│ /hub subdirectory usage │
│ - Fix Issue #9 : Silent failure on corrupted models with empty snapshots directories │
│ - Enhanced download throttling with adaptive delays (512KB chunks, 2-3s for large files) │
│ - Added migration warnings for legacy cache locations with clear user guidance │
│ - Improved corruption detection and deletion workflow consistency │
│ │
│ Technical improvements: │
│ - Unified cache architecture: CACHE_ROOT/hub for both default and HF_HOME scenarios │
│ - Exception-safe memory management with enhanced baseline tracking │
│ - Updated dependencies to latest tested versions (Python 3.9-3.13 support) │
│ - All 105 tests passing with real MLX model verification
2025-08-18 14:02:30 +02:00
8b0db287e4
Release MLX Knife 1.0.1 - Update PyPI Package Description
2025-08-15 23:32:58 +02:00
29548fe3f1
Release MLX Knife 1.0.0 - Stable Release with PyPI Publication
...
Major milestone: First stable release with official PyPI distribution.
New Features:
- PyPI publication: Now installable via \`pip install mlx-knife\`
- Official CLI-only designation with clear API policy
- Absolute GitHub URLs for PyPI package display (logo + demo)
Documentation Updates:
- All docs updated to v1.0.0 (README, CHANGELOG, TESTING, SECURITY, CLAUDE.md)
- Added PyPI installation instructions to README
- Updated supported versions tables
- Clarified CLI-only usage policy
Release Highlights:
- Transition from 1.0-rc3 to stable 1.0.0
- Production-ready with 104/104 tests passing
- Global accessibility via PyPI distribution
- Comprehensive documentation overhaul
Ready for community adoption and production use.
2025-08-15 13:57:26 +02:00
8e65ef03c7
Update README.md broke-cluster hint
...
Broke Cluster projekt link in README.md footer section
2025-08-14 17:20:24 +02:00
47af2c7096
Release MLX Knife 1.0-rc3 Resolves GitHub Issues #1 , #2 , #3 :
...
- Fix #1 : Partial name filtering for `mlxk list` command
- Fix #2 : Fuzzy matching for single-model commands
- Fix #3 : Default behavior for `mlxk health` (no --all flag required)
- Expanded test suite to 104/104 tests passing
2025-08-14 14:06:26 +02:00
01229cb6ef
Release MLX Knife 1.0-rc2: Enhanced Memory Management & Exception Safety
...
**Key Improvements**
- Robust exception handling during model loading with guaranteed cleanup
- Protection against nested context manager usage in MLXRunner
- Safe cleanup that handles partial loading failures gracefully
- Exception-resilient cache clearing operations
- Safe tokenizer attribute access with proper defaults
- Graceful memory statistics handling when metrics unavailable
- Comprehensive unit test coverage for memory management edge cases
**Changes**
- Updated version to 1.0-rc2 across all documentation files
- Enhanced MLXRunner context manager with bulletproof exception safety
- Added comprehensive unit tests for memory management scenarios
- Improved error handling for partial model loading failures
- Updated test coverage documentation (96/96 tests passing)
- Refined README to focus on key features rather than test metrics
This release focuses on production-ready memory management and exception
safety, making MLX Knife more robust for real-world usage scenarios.
2025-08-13 20:52:34 +02:00
b927fa1e33
Update documentation and remove GitHub Actions - no testing on github possible
...
- Remove .github/workflows/tests.yml (local testing only)
- Update CONTRIBUTING.md with current development workflow
- Refine README.md for 1.0-rc1 release readiness
- Update TESTING.md with comprehensive testing guide
2025-08-13 16:14:15 +02:00
The BROKE Cluster Team