Jiagan Cheng 85b4ae26b7 [https://nvbugs/5451342][fix] Use runtime max_batch_size when cuda_graph_config.max_batch_size is not provided in trtllm-bench (#7031) ... Signed-off-by: Jiagan Cheng <jiaganc@nvidia.com>		2025-08-26 08:10:35 -04:00
..
benchmark	[https://nvbugs/5453667] [fix] reverting a breaking change: make trtllm-bench enable_chunked_context defaults backend-dependent (#6956)	2025-08-16 00:29:02 -04:00
build	[None][fix] Remove expand configuration from mamba2 mixer (#6521)	2025-08-05 04:18:25 -04:00
dataclasses	[https://nvbugs/5451342][fix] Use runtime max_batch_size when cuda_graph_config.max_batch_size is not provided in trtllm-bench (#7031)	2025-08-26 08:10:35 -04:00
utils	Enable trtllm-bench to run LoRA and add basic e2e perf testing capability for LoRA in PyT flow (#5130)	2025-06-15 18:54:04 +03:00
__init__.py	Update TensorRT-LLM	2024-08-20 18:55:15 +08:00