"docs/features/quantization/quark.md" did not exist on "d0bc2f810b7a34247154b078c2429bf62519e9ca"
Unverified Commit 366f6b3a authored by Cyrus Leung's avatar Cyrus Leung Committed by GitHub
Browse files

[Bugfix] Fix multi-api server not working for text models (#21933)


Signed-off-by: default avatarDarkLight1337 <tlleungac@connect.ust.hk>
parent 6e599eeb
......@@ -856,7 +856,7 @@ class ModelConfig:
self.tokenizer = s3_tokenizer.dir
def _init_multimodal_config(self) -> Optional["MultiModalConfig"]:
if self.registry.is_multimodal_model(self.architectures, self):
if self._model_info.supports_multimodal:
return MultiModalConfig(
limit_per_prompt=self.limit_mm_per_prompt,
media_io_kwargs=self.media_io_kwargs,
......@@ -865,19 +865,6 @@ class ModelConfig:
disable_mm_preprocessor_cache,
interleave_mm_strings=self.interleave_mm_strings)
if self.limit_mm_per_prompt:
raise ValueError("`limit_mm_per_prompt` is only supported for "
"multimodal models.")
if self.mm_processor_kwargs:
raise ValueError("`mm_processor_kwargs` is only supported for "
"multimodal models.")
if self.disable_mm_preprocessor_cache:
raise ValueError("`disable_mm_preprocessor_cache` is only "
"supported for multimodal models.")
if self.interleave_mm_strings:
raise ValueError("`interleave_mm_strings` is only "
"supported for multimodal models.")
return None
def _get_encoder_config(self):
......
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