[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
@@ -17,7 +17,7 @@ import logging
from typing import Literal
import pytest
from transformers import PretrainedConfig
from transformers import PreTrainedConfig
from vllm.config.model import ModelConfig
from vllm.config.parallel import ParallelConfig
@@ -46,7 +46,7 @@ def _override_logged(caplog: pytest.LogCaptureFixture) -> bool:
@pytest.mark.cpu_test
def test_override_raises_smaller_value(vllm_caplog: pytest.LogCaptureFixture):
hf_config = PretrainedConfig(max_position_embeddings=2048)
hf_config = PreTrainedConfig(max_position_embeddings=2048)
SpeculativeConfig._maybe_override_draft_max_position_embeddings(
hf_config, target_max_model_len=8192
)
@@ -56,7 +56,7 @@ def test_override_raises_smaller_value(vllm_caplog: pytest.LogCaptureFixture):
@pytest.mark.cpu_test
def test_override_keeps_sufficient_value(vllm_caplog: pytest.LogCaptureFixture):
hf_config = PretrainedConfig(max_position_embeddings=8192)
hf_config = PreTrainedConfig(max_position_embeddings=8192)
SpeculativeConfig._maybe_override_draft_max_position_embeddings(
hf_config, target_max_model_len=8192
)
@@ -66,7 +66,7 @@ def test_override_keeps_sufficient_value(vllm_caplog: pytest.LogCaptureFixture):
@pytest.mark.cpu_test
def test_override_ignores_missing_attribute(vllm_caplog: pytest.LogCaptureFixture):
hf_config = PretrainedConfig()
hf_config = PreTrainedConfig()
hf_config.__dict__.pop("max_position_embeddings", None)
SpeculativeConfig._maybe_override_draft_max_position_embeddings(
hf_config, target_max_model_len=8192