Ke Wen 20142ab542 Simplify Tensor Parallel implementation with PyTorch TP (#34184) ... * Simplify Tensor Parallel implementation with PyTorch TP * Move tp_plan to config * Lint * Format and warning * Disable copy-from check * Conditionally get attr from config * make fix-copies * Move base_model_tp_plan to PretrainedConfig * Move TP into from_pretrained * Add device context for load * Do not serialize * Move _tp_plan setting to post_init * Add has_tp_plan * Add test_tp * Add 'Multi-gpu inference' doc * Add backward support for device type identification * Auto-detect accelerator * supports_tp_plan * copyright year * Fix copy		2024-11-18 19:51:49 +01:00
..
test_tp.py	Simplify Tensor Parallel implementation with PyTorch TP (#34184)	2024-11-18 19:51:49 +01:00