mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-05 02:31:33 +08:00
|
|
||
|---|---|---|
| .. | ||
| _tensorrt_engine | ||
| _torch | ||
| bench | ||
| commands | ||
| evaluate | ||
| executor | ||
| inputs | ||
| layers | ||
| llmapi | ||
| metrics | ||
| models | ||
| plugin | ||
| quantization | ||
| runtime | ||
| scaffolding | ||
| serve | ||
| tokenizer | ||
| tools | ||
| __init__.py | ||
| _common.py | ||
| _dlpack_utils.py | ||
| _ipc_utils.py | ||
| _mnnvl_utils.py | ||
| _ray_utils.py | ||
| _utils.py | ||
| builder.py | ||
| disaggregated_params.py | ||
| functional.py | ||
| graph_rewriting.py | ||
| logger.py | ||
| lora_helper.py | ||
| lora_manager.py | ||
| mapping.py | ||
| math_utils.py | ||
| module.py | ||
| network.py | ||
| parameter.py | ||
| profiler.py | ||
| prompt_adapter_manager.py | ||
| python_plugin.py | ||
| ray_stub.py | ||
| sampling_params.py | ||
| scheduling_params.py | ||
| serialization.py | ||
| top_model_mixin.py | ||
| version.py | ||