[Bugfix] Normalize malformed dict prompts that carry token IDs in prompt (#40339)

Signed-off-by: Alchuang22-dev <2584829494@qq.com>
This commit is contained in:
Zeyu Zhang
2026-04-21 07:44:36 +00:00
committed by GitHub
parent f95c11a848
commit 5a94a19824
3 changed files with 57 additions and 2 deletions
+10
View File
@@ -435,6 +435,11 @@ class BaseRenderer(ABC, Generic[_T]):
params: TokenizeParams,
) -> SingletonTokPrompt:
if "prompt_token_ids" not in prompt and "prompt_embeds" not in prompt:
if not isinstance(prompt.get("prompt"), str):
raise TypeError(
"Expected prompt['prompt'] to be a string before tokenization; "
"use 'prompt_token_ids' for token ID inputs"
)
prompt = params.apply_pre_tokenization(self.tokenizer, prompt) # type: ignore[arg-type]
prompt = self._tokenize_prompt(prompt, params)
@@ -466,6 +471,11 @@ class BaseRenderer(ABC, Generic[_T]):
params: TokenizeParams,
) -> SingletonTokPrompt:
if "prompt_token_ids" not in prompt and "prompt_embeds" not in prompt:
if not isinstance(prompt.get("prompt"), str):
raise TypeError(
"Expected prompt['prompt'] to be a string before tokenization; "
"use 'prompt_token_ids' for token ID inputs"
)
prompt = params.apply_pre_tokenization(self.tokenizer, prompt) # type: ignore[arg-type]
prompt = await self._tokenize_prompt_async(prompt, params)