[Feature] ThreadPoolExecutor async fill_token_bitmask (#5083)

* ThreadPoolExecutor async fill_token_bitmask

* ThreadPoolExecutor async fill_token_bitmask logging

* fix test_guided_decoding

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* add fill_bitmask_parallel_batch_size ENV

* FD_FILL_BITMASK_BATCH fastdeploy.envs

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Daci
2025-11-19 10:04:16 +08:00
committed by GitHub
parent 4a7739ec0b
commit eab8384da6
6 changed files with 76 additions and 16 deletions

View File

@@ -1417,7 +1417,6 @@ class StructuredOutputsConfig:
# disable any whitespace for guided decoding
self.disable_any_whitespace: bool = True
self.logits_processors: Optional[list[str]] = None
for key, value in args.items():
if hasattr(self, key) and value != "None":
setattr(self, key, value)