apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Bugfix] Align thinking_budget behavior with ERNIE reasoning flow (#6934)

Browse Source 
* [Bugfix] Align thinking_budget behavior with ERNIE reasoning flow

* [Docs] Fix thinking_budget markdown formatting

* [Test] Align ernie thinking budget test with process_request_dict
This commit is contained in:
jackyYang6
2026-03-23 14:15:55 +08:00
committed by GitHub
parent 7a78001be2
commit 634d23a38a
10 changed files with 663 additions and 285 deletions
Download Patch File Download Diff File Expand all files Collapse all files
fastdeploy/input/ernie4_5_processor.py
+9
View File
@@ -107,6 +107,11 @@ class Ernie4_5Processor(BaseDataProcessor):
bad_words_token_ids = self.update_bad_words(bad_words, bad_words_token_ids)
request["bad_words_token_ids"] = bad_words_token_ids
logits_processors_args = self._prepare_think_stop_sentence(
request.get("logits_processors_args") or {}, max_model_len
)
request["logits_processors_args"] = logits_processors_args
# processing prompt_token_ids
if not request.get("prompt_token_ids"):
if request.get("prompt"):
@@ -143,6 +148,10 @@ class Ernie4_5Processor(BaseDataProcessor):
# truncate prompts that exceed the length limit
if max_model_len is not None and len(request["prompt_token_ids"]) > max_model_len:
request["prompt_token_ids"] = request["prompt_token_ids"][: max_model_len - 1]
logits_processors_args = self._update_thinking_prompt_state(
request["prompt_token_ids"], request.get("logits_processors_args") or {}
)
request["logits_processors_args"] = logits_processors_args
max_tokens = max_model_len - len(request["prompt_token_ids"])
if request.get("max_tokens") is None:
request["max_tokens"] = max(1, max_tokens)