[Chore] Use Transformers v5 names and drop redundant processor use_fast (#58550)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-09-24 14:14:10 +00:00
committed by GitHub
co-authored by Claude Opus 5.5
parent 484c211fe8
commit d881812500
218 changed files with 869 additions and 813 deletions
+2 -2
View File
@@ -6,7 +6,7 @@ from vllm.logger import init_logger
from vllm.utils.math_utils import round_up
if TYPE_CHECKING:
from transformers import PretrainedConfig
from transformers import PreTrainedConfig
from vllm.config import CacheConfig, ModelConfig, VllmConfig
from vllm.config.cache import MambaDType
@@ -681,7 +681,7 @@ class NemotronHForCausalLMConfig(VerifyAndUpdateConfig):
@classmethod
def update_mamba_ssm_cache_dtype(
cls, *, cache_config: "CacheConfig", hf_config: "PretrainedConfig"
cls, *, cache_config: "CacheConfig", hf_config: "PreTrainedConfig"
) -> None:
"""Update mamba_ssm_cache_dtype for NemotronH models when set to 'auto'
(or not explicitly set), to the value specified in the HF config, or to