log Generation Prompt

backend-python/routes/state_cache.py

@@ -87,7 +87,7 @@ def longest_prefix_state(body: LongestPrefixStateBody, request: Request):
         v = dtrie[id]
         device = v["device"]
         prompt = trie[id]
-        quick_log(request, body, "Hit: " + prompt)
+        quick_log(request, body, "Hit:\n" + prompt)
         return {
             "prompt": prompt,
             "tokens": v["tokens"],

backend-python/utils/log.py

@@ -22,7 +22,7 @@ def quick_log(request: Request, body: Any, response: str):
             if body
             else ""
         )
-        + (f"Response:\n{response}\n" if response else "")
+        + (f"Data:\n{response}\n" if response else "")
     )
 
 

backend-python/utils/rwkv.py

@@ -2,6 +2,7 @@ import os
 import pathlib
 import copy
 from typing import Dict, List
+from utils.log import quick_log
 from fastapi import HTTPException
 from pydantic import BaseModel, Field
 from rwkv_pip.utils import PIPELINE
@@ -101,6 +102,7 @@ The following is a coherent verbose detailed conversation between a girl named {
         return out
 
     def generate(self, prompt: str, stop: str = None):
+        quick_log(None, None, "Generation Prompt:\n" + prompt)
         cache = None
         delta_prompt = prompt
         try: