apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[FDConfig]Remove max_num_batched_tokens/max_num_seqs in parallel config (#4116)

Browse Source 
* remove max_num_batched_tokens in parallel config

* remove max_num_seqs

* update test case

* fix test

* fix

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
This commit is contained in:
YuanRisheng
2025-09-17 10:43:35 +08:00
committed by GitHub
parent c01a756912
commit 2e9e53ff7e
30 changed files with 169 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/utils.py
View File

@@ -21,6 +21,7 @@ from fastdeploy.config import (
FDConfig,
GraphOptimizationConfig,
ParallelConfig,
SchedulerConfig,
)
@@ -50,12 +51,17 @@ class FakeModelConfig:
def get_default_test_fd_config():
graph_opt_config = GraphOptimizationConfig(args={})
scheduler_config = SchedulerConfig(args={})
scheduler_config.max_num_seqs = 1
parallel_config = ParallelConfig(args={})
parallel_config.max_num_seqs = 1
parallel_config.data_parallel_rank = 1
cache_config = CacheConfig({})
fd_config = FDConfig(
graph_opt_config=graph_opt_config, parallel_config=parallel_config, cache_config=cache_config, test_mode=True
graph_opt_config=graph_opt_config,
parallel_config=parallel_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
test_mode=True,
)
fd_config.model_config = FakeModelConfig()
return fd_config