xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 18:54:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-05-04 06:59:24 +08:00 committed by GitHub
parent f66f1e0fa3
commit 46fae69cf0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/arg_utils.py
View File

@ -1237,6 +1237,12 @@ class EngineArgs:
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:

3
vllm/inputs/preprocess.py
View File

@ -6,7 +6,6 @@ from typing import Any, Optional, Union, cast
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
@ -306,8 +305,6 @@ class InputPreprocessor:
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"]