Snider 19c4823b04 feat(metal): add Llama 3 model support (Llama 3.1 8B validated) ... Llama shares the Qwen3 loader (same decoder: pre-norm, SwiGLU, GQA). Model type now detected from config.json model_type field instead of weight-only heuristic. Llama 3 chat template and EOS token added. Model tests now clear Metal GPU cache between runs. Llama 3.1 8B Instruct 4-bit: 30 tok/s on M3 Ultra. Co-Authored-By: Virgil <virgil@lethean.io> Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-19 23:06:43 +00:00
..
metal	feat(metal): add Llama 3 model support (Llama 3.1 8B validated)	2026-02-19 23:06:43 +00:00