[Bugfix]Support Qwen3-MOE on aclgraph mode in sizes capture and add new ut (#2511)
[Bugfix]Support Qwen3-MOE on aclgraph mode in sizes capture and add new
ut
What this PR does / why we need it?
This PR solves the problem of sizes capture and stream error caused by
using ACLgraph on the Qwen3-30B MOE model.
Add new ut.
Does this PR introduce any user-facing change?
no
How was this patch tested?
ut
- vLLM version: v0.10.1.1
- vLLM main:
6fad29b11b
Signed-off-by: lilinsiman <lilinsiman@gmail.com>
This commit is contained in:
@@ -255,6 +255,9 @@ class TestUtils(TestBase):
|
||||
parallel_config=test_parallel_config,
|
||||
)
|
||||
utils.update_aclgraph_sizes(test_vllm_config)
|
||||
os.environ['HCCL_OP_EXPANSION_MODE'] = 'AIV'
|
||||
utils.update_aclgraph_sizes(test_vllm_config)
|
||||
del os.environ['HCCL_OP_EXPANSION_MODE']
|
||||
self.assertEqual(
|
||||
147,
|
||||
len(test_vllm_config.compilation_config.cudagraph_capture_sizes))
|
||||
@@ -267,6 +270,9 @@ class TestUtils(TestBase):
|
||||
parallel_config=test_parallel_config,
|
||||
)
|
||||
utils.update_aclgraph_sizes(test_vllm_config)
|
||||
os.environ['HCCL_OP_EXPANSION_MODE'] = 'AIV'
|
||||
utils.update_aclgraph_sizes(test_vllm_config)
|
||||
del os.environ['HCCL_OP_EXPANSION_MODE']
|
||||
self.assertEqual(
|
||||
3,
|
||||
len(test_vllm_config.compilation_config.cudagraph_capture_sizes))
|
||||
|
||||
Reference in New Issue
Block a user