mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-09-26 20:41:53 +08:00
initial commit (#4248)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
This commit is contained in:
@@ -235,9 +235,6 @@ class LLMEngine:
|
||||
request.get("max_tokens"),
|
||||
),
|
||||
)
|
||||
if request.get("reasoning_max_tokens") is None:
|
||||
default_reasoning_max_tokens = max(int(request.get("max_tokens") * 0.8), 1)
|
||||
request.set("reasoning_max_tokens", default_reasoning_max_tokens)
|
||||
min_tokens = request.get("min_tokens")
|
||||
if input_ids_len + min_tokens >= self.cfg.max_model_len:
|
||||
error_msg = (
|
||||
|
Reference in New Issue
Block a user