apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 00:06:38 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Fix bug for offline inference in scheduler v1 (#3117)

Browse Source
This commit is contained in:
chenjian
2025-07-31 17:54:24 +08:00
committed by GitHub
parent 583eae2fd1
commit 32307283f1
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/engine/engine.py
View File

@@ -500,6 +500,7 @@ class LLMEngine:
enable_thinking = kwargs.get("enable_thinking", None) enable_thinking = kwargs.get("enable_thinking", None)
request = self.data_processor.process_request(request, self.cfg.max_model_len, enable_thinking=enable_thinking) request = self.data_processor.process_request(request, self.cfg.max_model_len, enable_thinking=enable_thinking)
request.prompt_token_ids_len = len(request.prompt_token_ids) request.prompt_token_ids_len = len(request.prompt_token_ids)
request.need_prefill_tokens = request.prompt_token_ids_len
input_ids_len = request.prompt_token_ids_len input_ids_len = request.prompt_token_ids_len
request.set( request.set(
"max_tokens", "max_tokens",