apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-06 00:57:33 +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

18
tests/graph_optimization/test_graph_opt_backend.py
View File

@@ -25,6 +25,7 @@ from fastdeploy.config import (
FDConfig,
GraphOptimizationConfig,
ParallelConfig,
SchedulerConfig,
)
from fastdeploy.model_executor.forward_meta import ForwardMeta
from fastdeploy.model_executor.graph_optimization.decorator import (
@@ -85,15 +86,16 @@ class TestGraphOptBackend(unittest.TestCase):
baseline_graph_opt_config.use_cudagraph = False
baseline_graph_opt_config.graph_opt_level = 0
baseline_parallel_config = ParallelConfig(args={})
baseline_parallel_config.max_num_seqs = self.max_num_seqs
baseline_scheduler_config = SchedulerConfig(args={})
baseline_scheduler_config.max_num_seqs = self.max_num_seqs
baseline_cache_config = CacheConfig({})
baseline_parallel_config = ParallelConfig(args={})
self.baseline_fd_config = FDConfig(
graph_opt_config=baseline_graph_opt_config,
parallel_config=baseline_parallel_config,
scheduler_config=baseline_scheduler_config,
cache_config=baseline_cache_config,
parallel_config=baseline_parallel_config,
test_mode=True,
)
@@ -129,17 +131,19 @@ class TestGraphOptBackend(unittest.TestCase):
graph_opt_config.graph_opt_level = graph_opt_level
# Setup parallel config
parallel_config = ParallelConfig(args={})
parallel_config.max_num_seqs = self.max_num_seqs
scheduler_config = SchedulerConfig(args={})
scheduler_config.max_num_seqs = self.max_num_seqs
# Setup cache config
cache_config = CacheConfig({})
parallel_config = ParallelConfig(args={})
# Create FD config
return FDConfig(
graph_opt_config=graph_opt_config,
parallel_config=parallel_config,
scheduler_config=scheduler_config,
cache_config=cache_config,
parallel_config=parallel_config,
test_mode=True,
)