fix: In the runner, every 8 tokens yield

2026-06-26 07:24:20 +00:00 · 2025-08-03 23:23:51 +08:00
parent 48d11540ae
commit 44ac8b2b63
4 changed files with 20 additions and 20 deletions
@@ -286,8 +286,7 @@ class ModelScopeChatCompletions(requester.LLMAPIRequester):
                delta_message.is_final = True
                delta_message.content = current_content

-            if chunk_idx % 64 == 0 or delta_message.is_final:
-                yield delta_message
+            yield delta_message
            # return

    async def invoke_llm(