Chang Liu 01cb3ccb04 use global expert idx to load expert weights (#3386) ... Co-authored-by: hlu1 <14827759+hlu1@users.noreply.github.com>		2025-04-14 11:58:30 -07:00
..
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
attention.py	[Deepseek] Redesign multi-stream API (#3459)	2025-04-11 23:00:25 -07:00
decoder_layer.py	refactor: Remove _pp_forward. (#3496)	2025-04-14 09:49:44 +08:00
embedding.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
fused_moe.py	use global expert idx to load expert weights (#3386)	2025-04-14 11:58:30 -07:00
gated_mlp.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
linear.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
logits_procesor.py	Update (#2978)	2025-03-23 16:39:35 +08:00
mamba.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
mlp.py	refactor: remove ParallelConfig in tensorrt_llm._torch.distributed module (#3370)	2025-04-11 15:34:20 -07:00
multi_stream_utils.py	[Deepseek] Redesign multi-stream API (#3459)	2025-04-11 23:00:25 -07:00
rms_norm.py	Add Llama 4 (#3302)	2025-04-09 03:35:21 +08:00
rotary_embedding.py	feat: support llama4 nope layers; support FP8 checkpoint loading; (#3382)	2025-04-10 10:16:42 -07:00