amitz-nv e5407ea89a Fix torch nvsmall through pyexecutor and fix its TP support (#3238) ... * Fix NemotronNAS support Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>		2025-04-07 11:53:17 +03:00
..
__init__.py	Update (#2978)	2025-03-23 16:39:35 +08:00
.gitkeep	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
modeling_auto.py	Add initial EAGLE-3 implementation (#3035)	2025-03-29 22:31:24 +08:00
modeling_bert.py	Refactor imports inside tensorrt_llm._torch. (#3015)	2025-03-26 11:01:07 +08:00
modeling_deepseekv3.py	Raise error for PP + MTP (#3244)	2025-04-03 04:45:31 +08:00
modeling_llama.py	Add initial EAGLE-3 implementation (#3035)	2025-03-29 22:31:24 +08:00
modeling_llava_next.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
modeling_mamba_hybrid.py	Add initial EAGLE-3 implementation (#3035)	2025-03-29 22:31:24 +08:00
modeling_mixtral.py	feat: Optionally split MoE inputs into chunks to reduce GPU memory usage (#3104)	2025-04-01 16:07:02 +08:00
modeling_mllama.py	Update TensorRT-LLM (#2792)	2025-02-18 21:27:39 +08:00
modeling_multimodal_encoder.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
modeling_multimodal_utils.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
modeling_nemotron.py	Add initial EAGLE-3 implementation (#3035)	2025-03-29 22:31:24 +08:00
modeling_nvsmall.py	Fix torch nvsmall through pyexecutor and fix its TP support (#3238)	2025-04-07 11:53:17 +03:00
modeling_qwen2vl.py	Update (#2978)	2025-03-23 16:39:35 +08:00
modeling_qwen.py	Add initial EAGLE-3 implementation (#3035)	2025-03-29 22:31:24 +08:00
modeling_utils.py	fix deepseek failure with pipeline parallelism (#3225)	2025-04-02 22:56:39 +08:00
modeling_vila.py	fix vila test (#3042)	2025-04-04 14:30:06 +08:00