2 commits

Author	SHA1	Message	Date
Claude	e6ada25bd8	fix: add Metal cache management to prevent memory growth ... - Add ClearCache() wrapping mlx_clear_cache - Clear Metal allocator cache every 8 tokens during generation - Set 16GB cache limit on backend init - Prevents GPU memory from growing unbounded during inference Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-16 05:53:52 +00:00
Claude	8ee0c4bc4e	feat: add native MLX backend for Apple Silicon inference (pkg/mlx) ... CGo wrapper for mlx-c providing zero-Python Metal GPU inference. Includes Gemma 3 model architecture, BPE tokenizer, KV cache, composable sampling, and OpenAI-compatible serve command. Build-tagged (darwin && arm64 && mlx) with stubs for cross-platform. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-16 05:53:52 +00:00