apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 21 Packages Projects Releases Wiki Activity

[Feature] consider multimodal model when dummy run (#6045)

Browse Source 
* add mm do profile

* updata code

* update code

* update code

* update code

* update test case

* update code

* update code

* fix xpu bug

* update code

* add mm do profile

* update test case

* update code
This commit is contained in:
kevin
2026-02-09 17:49:55 +08:00
committed by GitHub
parent 783d56e28a
commit d60daca4a8
25 changed files with 166 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/v1/cache_manager/test_prefix_cache.py
+1
View File
@@ -34,6 +34,7 @@ def make_prefix_cache_manager(max_num_seqs, enable_mm=False, num_gpu_blocks_over
speculative_cfg = SimpleNamespace(method=None)
model_cfg.print = print
model_cfg.architectures = ["test_model"]
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
parallel_cfg = ParallelConfig(args)
scheduler_cfg = SchedulerConfig(args)
tests/v1/test_resource_manager_v1.py
+3
View File
@@ -80,6 +80,7 @@ def _build_manager(
model_cfg.print = print
model_cfg.max_model_len = max_model_len
model_cfg.architectures = architectures or ["test_model"]
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
cache_cfg.kv_cache_ratio = 1.0
parallel_cfg = ParallelConfig(args)
@@ -140,6 +141,7 @@ class TestResourceManagerV1(unittest.TestCase):
model_cfg.print = print
model_cfg.max_model_len = 3200
model_cfg.architectures = ["test_model"]
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
cache_cfg.kv_cache_ratio = 1.0
parallel_cfg = ParallelConfig(args)
@@ -301,6 +303,7 @@ class TestRevertChunkedMMInput(unittest.TestCase):
model_cfg.print = print
model_cfg.max_model_len = 3200
model_cfg.architectures = ["test_model"]
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
cache_cfg.kv_cache_ratio = 1.0
cache_cfg.block_size = 64
tests/v1/test_schedule_output.py
+3
View File
@@ -32,6 +32,7 @@ def test_normal_schedule():
speculative_cfg = SimpleNamespace(method=None)
model_cfg.print = print
model_cfg.max_model_len = 5120
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
parallel_cfg = ParallelConfig(args)
scheduler_cfg = SchedulerConfig(args)
@@ -97,6 +98,7 @@ def test_preempted_request():
speculative_cfg = SimpleNamespace(method=None)
model_cfg.print = print
model_cfg.max_model_len = 5120
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
parallel_cfg = ParallelConfig(args)
scheduler_cfg = SchedulerConfig(args)
@@ -163,6 +165,7 @@ def test_caching_output():
speculative_cfg = SimpleNamespace(method=None)
model_cfg.print = print
model_cfg.max_model_len = 5120
model_cfg.mm_max_tokens_per_item = None
cache_cfg.bytes_per_layer_per_block = 1
parallel_cfg = ParallelConfig(args)
scheduler_cfg = SchedulerConfig(args)