mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-12 14:03:48 +08:00
* committed APIs validation Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * fix Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * clean name Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * separate Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * add TODOs Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * fix naming Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * fix Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> --------- Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com>
36 lines
807 B
YAML
36 lines
807 B
YAML
methods:
|
|
__init__:
|
|
parameters:
|
|
calib_batch_size:
|
|
annotation: int
|
|
default: 1
|
|
calib_batches:
|
|
annotation: int
|
|
default: 512
|
|
calib_dataset:
|
|
annotation: str
|
|
default: cnn_dailymail
|
|
calib_max_seq_length:
|
|
annotation: int
|
|
default: 512
|
|
device:
|
|
annotation: Literal['cuda', 'cpu']
|
|
default: cuda
|
|
random_seed:
|
|
annotation: int
|
|
default: 1234
|
|
tokenizer_max_seq_length:
|
|
annotation: int
|
|
default: 2048
|
|
return_annotation: None
|
|
from_dict:
|
|
parameters:
|
|
config:
|
|
annotation: dict
|
|
default: inspect._empty
|
|
return_annotation: tensorrt_llm.llmapi.llm_utils.CalibConfig
|
|
to_dict:
|
|
parameters: {}
|
|
return_annotation: dict
|
|
properties: {}
|