biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Core] [Bugfix] Add Input Embeddings (#15428)

Browse Source 
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: 临景 <linjing.yx@alibaba-inc.com>
Co-authored-by: Bryce1010 <bryceyx@gmail.com>
Co-authored-by: Nan2018 <nan@protopia.ai>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Andrew Sansom
2025-05-02 03:06:39 -05:00
committed by GitHub
parent 9e2de9b9e9
commit cc2a77d7f1
22 changed files with 691 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/conftest.py
View File

@@ -787,7 +787,7 @@ class VllmRunner:
def get_inputs(
self,
prompts: list[str],
prompts: Union[list[str], list[torch.Tensor]],
images: Optional[PromptImageInput] = None,
videos: Optional[PromptVideoInput] = None,
audios: Optional[PromptAudioInput] = None,
@@ -809,16 +809,18 @@ class VllmRunner:
if audios is not None and (audio := audios[i]) is not None:
multi_modal_data["audio"] = audio
inputs.append(
TextPrompt(prompt=prompt,
multi_modal_data=multi_modal_data
if multi_modal_data else None))
text_prompt_kwargs = {
("prompt" if isinstance(prompt, str) else "prompt_embeds"):
prompt,
"multi_modal_data": multi_modal_data or None
}
inputs.append(TextPrompt(**text_prompt_kwargs))
return inputs
def generate(
self,
prompts: list[str],
prompts: Union[list[str], list[torch.Tensor]],
sampling_params: SamplingParams,
images: Optional[PromptImageInput] = None,
videos: Optional[PromptVideoInput] = None,
@@ -844,7 +846,7 @@ class VllmRunner:
output_str = sample.text
output_ids = list(sample.token_ids)
req_sample_output_ids.append(prompt_ids + output_ids)
req_sample_output_strs.append(prompt_str + output_str)
req_sample_output_strs.append((prompt_str or "") + output_str)
outputs.append((req_sample_output_ids, req_sample_output_strs))
return outputs
@@ -911,7 +913,7 @@ class VllmRunner:
def generate_greedy(
self,
prompts: list[str],
prompts: Union[list[str], list[torch.Tensor]],
max_tokens: int,
images: Optional[PromptImageInput] = None,
videos: Optional[PromptVideoInput] = None,