A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 4, 15:00 UTC
Deprecate support for Transformers v4 (#40389)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Harry Mellor committed
Apr 27, 2026 at 16:19 UTC
e6f710a87f3ce8b137d15ffa4b3a12568e1c8aa3
1 file changed
+7
vllm/transformers_utils/config.py
+7
@@ -66,6 +66,13 @@ MISTRAL_CONFIG_NAME = "params.json"
66
67
logger = init_logger(__name__)
68
69
+if Version(version("transformers")) < Version("5.0.0"):
70
+ logger.warning(
71
+ "Support for Transformers v4 is deprecated. The Transformers v4 codepath will "
72
+ "become unmaintained in vLLM v0.22.0 and will be removed in vLLM v0.24.0. "
73
+ "Please upgrade to Transformers v5: pip install --upgrade transformers"
74
+ )
75
+
76
77
class LazyConfigDict(dict):
78
def __getitem__(self, key):