apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-11-03 02:53:26 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

delete default value reasoning_max_tokens (#4250)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details

Browse Source 
* delete default value reasoning_max_tokens

* Adjust max_tokens and reasoning_max_tokens logic
This commit is contained in:
Yuanle Liu
2025-09-26 10:42:27 +08:00
committed by GitHub
parent 213f15ef55
commit dcf633c4d9
3 changed files with 4 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/input/ernie4_5_vl_processor/ernie4_5_vl_processor.py
View File

@@ -255,6 +255,10 @@ class Ernie4_5_VLProcessor(Ernie4_5Processor):
request["prompt_token_ids"] = request["prompt_token_ids"][: max_model_len - 1]
if request.get("max_tokens") is None:
request["max_tokens"] = max(1, max_model_len - len(request["prompt_token_ids"]))
else:
request["max_tokens"] = min(max_model_len - len(request["prompt_token_ids"]), request["max_tokens"])
if request.get("reasoning_max_tokens") is None:
request["reasoning_max_tokens"] = max(int(request["max_tokens"] * 0.8), 1)
data_processor_logger.info(f"Processed request {request}")
return request