Neta Zmora 1d6fbbf45d [#9236][feature] Make sharing of activation_type across SW layers more robust (#9238) ... C++, Python and Python MoE layer all share the definition of ActivationType. Currently this is done thru redefinition which is fragile and can break when adding new activation function types. tensorrt_llm/_torch/utils.py cpp/tensorrt_llm/kernels/cutlass_kernels/include/common.h => tensorrt_llm/layers/moe.py cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_kernels.cu Signed-off-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com> Signed-off-by: Neta Zmora <96238833+nzmora-nvidia@users.noreply.github.com> Co-authored-by: Kaiyu Xie <26294424+kaiyux@users.noreply.github.com>		2025-11-20 16:06:58 +08:00
..
__init__.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
activation.py	Update TensorRT-LLM (#787)	2024-01-02 17:54:32 +08:00
attention.py	[https://nvbugs/5302040][feat] Add whisper support (Bert Attention on SM100 and GPTAttention for cross attention on SM100) (#5527)	2025-08-13 11:19:13 -07:00
cast.py	Update TensorRT-LLM (#787)	2024-01-02 17:54:32 +08:00
conv.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
embedding.py	fix: #3137 speculative decoding and multimodal input support (#3276)	2025-04-09 23:40:19 +08:00
language_adapter.py	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
linear.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
lora.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
mlp.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
moe.py	[#9236][feature] Make sharing of activation_type across SW layers more robust (#9238)	2025-11-20 16:06:58 +08:00
normalization.py	Update TensorRT-LLM (#2849)	2025-03-04 18:44:00 +08:00
pooling.py	Update TensorRT-LLM (#787)	2024-01-02 17:54:32 +08:00
recurrent.py	Update TensorRT-LLM (#1954)	2024-07-16 15:30:25 +08:00
ssm.py	Update TensorRT-LLM (#2562)	2024-12-11 00:31:05 -08:00