Skip to content

GitLab

Unverified Commit 87185c88 authored by Maryam Tahhan's avatar Maryam Tahhan Committed by GitHub
Browse files

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


Signed-off-by: default avatarMaryam Tahhan <mtahhan@redhat.com>
parent 9cf4edae
Hide whitespace changes
Inline Side-by-side
Showing with 20 additions and 10 deletions
vllm/config/model.py
View file @ 87185c88
...@@ -585,16 +585,26 @@ class ModelConfig: ...@@ -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
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment