Skip to content

[Frontend] Perform offline path replacement to tokenizer #29706

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 29, 2025
+27 −6
Merged

[Frontend] Perform offline path replacement to tokenizer #29706

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1e05f12
Log offline model path replacement only when `model` changes
a4lg Nov 28, 2025
d6de5f3
Perform offline path replacement to `tokenizer`
a4lg Nov 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions tests/entrypoints/offline_mode/test_offline_mode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,16 @@
"max_num_seqs": 64,
"tensor_parallel_size": 1,
},
{
"model": "Qwen/Qwen3-0.6B",
"enforce_eager": True,
"gpu_memory_utilization": 0.50,
"max_model_len": 64,
"max_num_batched_tokens": 64,
"max_num_seqs": 64,
"tensor_parallel_size": 1,
"tokenizer": "Qwen/Qwen3-4B",
},
{
"model": "mistralai/Mistral-7B-Instruct-v0.1",
"enforce_eager": True,
Expand Down
23 changes: 17 additions & 6 deletions vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -581,15 +581,26 @@ def __post_init__(self):
from vllm.plugins import load_general_plugins

load_general_plugins()
# when use hf offline,replace model id to local model path
# when use hf offline,replace model and tokenizer id to local model path
if huggingface_hub.constants.HF_HUB_OFFLINE:
model_id = self.model
self.model = get_model_path(self.model, self.revision)
logger.info(
"HF_HUB_OFFLINE is True, replace model_id [%s] to model_path [%s]",
model_id,
self.model,
)
if model_id is not self.model:
logger.info(
"HF_HUB_OFFLINE is True, replace model_id [%s] to model_path [%s]",
model_id,
self.model,
)
if self.tokenizer is not None:
tokenizer_id = self.tokenizer
self.tokenizer = get_model_path(self.tokenizer, self.tokenizer_revision)
if tokenizer_id is not self.tokenizer:
logger.info(
"HF_HUB_OFFLINE is True, replace tokenizer_id [%s] "
"to tokenizer_path [%s]",
tokenizer_id,
self.tokenizer,
)

@staticmethod
def add_cli_args(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
Expand Down