mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
b2f69db507
* add eval_llmapi Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> tmp commit port to CLI tool Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> move Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> setup llmapi Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> fix spec_dec_algo Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> _update_from_hf_quant_config Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> fix Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> migrate test_pytorch.py Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> fix fp8 block scales Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> fix fp8 rowwise Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> adj alpha Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> move test_pytorch.py cases Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> move Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> rename test_accuracy.py to test_cli.py Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> clean Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * fix cnn_dailymail Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * renaming to cli flow Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * rename MMLU Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * rename Signed-off-by: Enwei Zhu <21126786+syuoni@users.noreply.github.com> * add error 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
1.1 KiB
Python
36 lines
1.1 KiB
Python
from ..disaggregated_params import DisaggregatedParams
|
|
from ..executor import CompletionOutput, RequestError
|
|
from ..sampling_params import GuidedDecodingParams, SamplingParams
|
|
from .build_cache import BuildCacheConfig
|
|
from .llm import LLM, RequestOutput
|
|
from .llm_args import (EagleDecodingConfig, LookaheadDecodingConfig,
|
|
MedusaDecodingConfig, MTPDecodingConfig)
|
|
from .llm_utils import (BuildConfig, CalibConfig, CapacitySchedulerPolicy,
|
|
KvCacheConfig, KvCacheRetentionConfig, QuantAlgo,
|
|
QuantConfig, SchedulerConfig)
|
|
from .mpi_session import MpiCommSession
|
|
|
|
__all__ = [
|
|
'LLM',
|
|
'CompletionOutput',
|
|
'RequestOutput',
|
|
'GuidedDecodingParams',
|
|
'SamplingParams',
|
|
'DisaggregatedParams',
|
|
'KvCacheConfig',
|
|
'KvCacheRetentionConfig',
|
|
'LookaheadDecodingConfig',
|
|
'MedusaDecodingConfig',
|
|
'EagleDecodingConfig',
|
|
'MTPDecodingConfig',
|
|
'SchedulerConfig',
|
|
'CapacitySchedulerPolicy',
|
|
'BuildConfig',
|
|
'QuantConfig',
|
|
'QuantAlgo',
|
|
'CalibConfig',
|
|
'BuildCacheConfig',
|
|
'RequestError',
|
|
'MpiCommSession',
|
|
]
|