Skip to content

[Misc] V0 fallback for --enable-prompt-embeds #17615

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 1 commit into from
May 3, 2025
Merged

[Misc] V0 fallback for --enable-prompt-embeds #17615

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 6 additions & 0 deletions vllm/engine/arg_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1237,6 +1237,12 @@ def _is_v1_supported_oracle(self, model_config: ModelConfig) -> bool:
recommend_to_remove=False)
return False

# No text embedding inputs so far.
if self.enable_prompt_embeds:
_raise_or_fallback(feature_name="--enable-prompt-embeds",
recommend_to_remove=False)
return False

# Only Fp16 and Bf16 dtypes since we only support FA.
V1_SUPPORTED_DTYPES = [torch.bfloat16, torch.float16]
if model_config.dtype not in V1_SUPPORTED_DTYPES:
Expand Down
3 changes: 0 additions & 3 deletions vllm/inputs/preprocess.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,6 @@

from typing_extensions import assert_never

from vllm import envs
from vllm.config import ModelConfig
from vllm.logger import init_logger
from vllm.lora.request import LoRARequest
Expand Down Expand Up @@ -306,8 +305,6 @@ def _process_embeds(
if not self.model_config.enable_prompt_embeds:
raise ValueError("You must set `--enable-prompt-embeds` to input "
"`prompt_embeds`.")
if envs.VLLM_USE_V1:
raise ValueError("`prompt_embeds` is only available in V0.")

prompt_embeds = parsed_content["prompt_embeds"]

Expand Down