apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Entropy calculation support (#5692)
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 
* support entropy

* fix bug

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
GoldPancake
2025-12-23 21:19:47 +08:00
committed by GitHub
parent d1c6e57341
commit 23d488c488
11 changed files with 369 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
fastdeploy/engine/args_utils.py
View File

@@ -509,6 +509,11 @@ class EngineArgs:
Whether to skip port availability check. Default is False (not skip).
"""
enable_entropy: bool = False
"""
Flag to enable entropy output. Default is False (disabled).
"""
def __post_init__(self):
"""
Post-initialization processing to set default tokenizer if not provided.
@@ -854,6 +859,12 @@ class EngineArgs:
default=EngineArgs.logits_processors,
help="FQCNs (Fully Qualified Class Names) of logits processors supported by the service.",
)
model_group.add_argument(
"--enable-entropy",
action="store_true",
default=EngineArgs.enable_entropy,
help="Enable output of token-level entropy.",
)
# Parallel processing parameters group
parallel_group = parser.add_argument_group("Parallel Configuration")