TensorRT-LLMs/tensorrt_llm/bench
Frank 1e317c98c6
[feat]: Allow for a settable end-of-sequence/padding token in max throughput benchmark. (#3776)
* Move world options to a different group for clarity.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

* Add eos_id option.

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>

---------

Signed-off-by: Frank Di Natale <3429989+FrankD412@users.noreply.github.com>
2025-05-01 09:42:46 +08:00
..
benchmark [feat]: Allow for a settable end-of-sequence/padding token in max throughput benchmark. (#3776) 2025-05-01 09:42:46 +08:00
build feat: adding multimodal (only image for now) support in trtllm-bench (#3490) 2025-04-18 07:06:16 +08:00
dataclasses [TRTLLM-4883][fix]: Update output speed calculation. (#3923) 2025-04-29 11:04:12 +08:00
utils feat: adding multimodal (only image for now) support in trtllm-bench (#3490) 2025-04-18 07:06:16 +08:00
__init__.py Update TensorRT-LLM 2024-08-20 18:55:15 +08:00