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

13
tests/graph_optimization/test_cuda_graph_spec_decode.py
View File

@@ -23,6 +23,7 @@ from fastdeploy.config import (
FDConfig,
GraphOptimizationConfig,
ParallelConfig,
SchedulerConfig,
)
from fastdeploy.model_executor.forward_meta import ForwardMeta
from fastdeploy.model_executor.graph_optimization.decorator import (
@@ -99,16 +100,18 @@ class TestCUDAGrpahSpecDecode(unittest.TestCase):
"""Run test case"""
graph_opt_config = GraphOptimizationConfig(args={})
graph_opt_config.use_cudagraph = True
parallel_config = ParallelConfig(args={})
parallel_config.max_num_seqs = 1
scheduler_config = SchedulerConfig(args={})
scheduler_config.max_num_seqs = 1
cache_config = CacheConfig({})
parallel_config = ParallelConfig(args={})
# Initialize cuda graph capture list
graph_opt_config._set_cudagraph_sizes(max_num_seqs=parallel_config.max_num_seqs)
graph_opt_config.init_with_cudagrpah_size(max_capture_size=parallel_config.max_num_seqs)
graph_opt_config._set_cudagraph_sizes(max_num_seqs=scheduler_config.max_num_seqs)
graph_opt_config.init_with_cudagrpah_size(max_capture_size=scheduler_config.max_num_seqs)
fd_config = 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,
)