xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 12:55:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Make deprecated --task embedding consistent with `--runner… (#29312)

Browse Source 
Signed-off-by: Maryam Tahhan <mtahhan@redhat.com>
This commit is contained in:
Maryam Tahhan 2025-11-25 03:19:52 +00:00 committed by GitHub
parent 9cf4edae6e
commit 87185c88d5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
vllm/config/model.py
View File

@ -585,16 +585,26 @@ class ModelConfig:
else: # task == "auto" else: # task == "auto"
pass pass
else: else:
debug_info = { # Neither generative nor pooling model - try to convert if possible
"architectures": architectures, if is_pooling_task:
"is_generative_model": is_generative_model, runner = "pooling"
"is_pooling_model": is_pooling_model, convert = _task_to_convert(self.task)
} msg_hint = (
raise AssertionError( "Please replace this option with `--runner pooling "
"The model should be a generative or " f"--convert {convert}` to continue using this model "
"pooling model when task is set to " "as a pooling model."
f"{self.task!r}. Found: {debug_info}" )
) else:
debug_info = {
"architectures": architectures,
"is_generative_model": is_generative_model,
"is_pooling_model": is_pooling_model,
}
raise AssertionError(
"The model should be a generative or "
"pooling model when task is set to "
f"{self.task!r}. Found: {debug_info}"
)
self.runner = runner self.runner = runner
self.convert = convert self.convert = convert