apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 08:37:06 +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

14
tests/utils/test_config.py
View File

@@ -6,6 +6,7 @@ from fastdeploy.config import (
FDConfig,
GraphOptimizationConfig,
ParallelConfig,
SchedulerConfig,
)
@@ -14,10 +15,12 @@ class TestConfig(unittest.TestCase):
parallel_config = ParallelConfig({"tensor_parallel_size": 16, "expert_parallel_size": 1})
graph_opt_config = GraphOptimizationConfig({})
cache_config = CacheConfig({})
scheduler_config = SchedulerConfig({})
fd_config = FDConfig(
parallel_config=parallel_config,
graph_opt_config=graph_opt_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
ips=["1.1.1.1", "0.0.0.0"],
test_mode=True,
)
@@ -28,10 +31,12 @@ class TestConfig(unittest.TestCase):
parallel_config = ParallelConfig({})
graph_opt_config = GraphOptimizationConfig({})
cache_config = CacheConfig({})
scheduler_config = SchedulerConfig({})
fd_config = FDConfig(
parallel_config=parallel_config,
graph_opt_config=graph_opt_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
ips="0.0.0.0",
test_mode=True,
)
@@ -42,26 +47,29 @@ class TestConfig(unittest.TestCase):
graph_opt_config = GraphOptimizationConfig({})
cache_config = CacheConfig({})
cache_config.enable_chunked_prefill = True
scheduler_config = SchedulerConfig({})
fd_config = FDConfig(
parallel_config=parallel_config,
graph_opt_config=graph_opt_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
ips="0.0.0.0",
test_mode=True,
)
if not envs.ENABLE_V1_KVCACHE_SCHEDULER:
assert fd_config.max_num_batched_tokens == 2048
assert fd_config.scheduler_config.max_num_batched_tokens == 2048
cache_config.enable_chunked_prefill = False
fd_config = FDConfig(
parallel_config=parallel_config,
graph_opt_config=graph_opt_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
ips="0.0.0.0",
test_mode=True,
)
if not envs.ENABLE_V1_KVCACHE_SCHEDULER:
assert fd_config.max_num_batched_tokens == 8192
assert fd_config.scheduler_config.max_num_batched_tokens == 8192
def test_fdconfig_init_cache(self):
parallel_config = ParallelConfig({})
@@ -69,10 +77,12 @@ class TestConfig(unittest.TestCase):
cache_config = CacheConfig({})
cache_config.cache_transfer_protocol = "rdma,ipc"
cache_config.pd_comm_port = "2334"
scheduler_config = SchedulerConfig({})
fd_config = FDConfig(
parallel_config=parallel_config,
graph_opt_config=graph_opt_config,
cache_config=cache_config,
scheduler_config=scheduler_config,
splitwise_role="prefill",
test_mode=True,
)