[Deprecate] Deprecate LLM.reward offline api, use LLM.encode instead. (#40688)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
wang.yuqi
2026-04-24 05:37:50 +00:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Cyrus Leung
parent c662b4359e
commit 9744b699ba
11 changed files with 203 additions and 38 deletions
+1 -1
View File
@@ -1183,7 +1183,7 @@ class VllmRunner:
return [req_output.outputs.data for req_output in req_outputs]
def reward(self, prompts: list[str]) -> list[list[float]]:
req_outputs = self.llm.reward(prompts)
req_outputs = self.llm.encode(prompts, pooling_task="token_classify")
return [req_output.outputs.data for req_output in req_outputs]
def score(