[Bugfix] Fix mc2 operator error in aclgraph + ep<16 scenario (#2609)
### What this PR does / why we need it? 1. quickfix mc2 operator error in aclgraph + ep<16 scenario to recover CI, will be refactorred in the future 2. disable aclgraph when testing w8a8 ### How was this patch tested? CI passed with existing test. - vLLM version: v0.10.1.1 - vLLM main: https://github.com/vllm-project/vllm/commit/95089607fa307c5facfb9706ea919292fb56e78c Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
1 parent
ee6d141dd4
commit
91c35d765a
2 files changed
+4
-2
No files matched your search
@@ -55,6 +55,7 @@ def test_models_distributed_Qwen3_MOE_TP2_WITH_EP():
|
||||
tensor_parallel_size=2,
|
||||
enable_expert_parallel=True,
|
||||
distributed_executor_backend="mp",
|
||||
enforce_eager=False,
|
||||
) as vllm_model:
|
||||
vllm_model.generate_greedy(example_prompts, max_tokens)
|
||||
|
||||
@@ -71,7 +72,7 @@ def test_models_distributed_Qwen3_MOE_W8A8():
|
||||
dtype=dtype,
|
||||
tensor_parallel_size=2,
|
||||
quantization="ascend",
|
||||
enforce_eager=False,
|
||||
enforce_eager=True,
|
||||
) as vllm_model:
|
||||
vllm_model.generate_greedy(example_prompts, max_tokens)
|
||||
|
||||
|
||||
@@ -242,7 +242,8 @@ class AscendFusedMoE(FusedMoE):
|
||||
moe_comm_method_name = forward_context.moe_comm_method_name
|
||||
|
||||
# TODO: Can we refactor this logic to model_runner?
|
||||
if not self.moe_config.use_ep:
|
||||
# TODO: Adjusted logic to differentiate between A2 and A3, we check ep_size here since mc2 only support ep_size >= 16 on A3 now
|
||||
if self.moe_config.ep_size < 16:
|
||||
moe_comm_method_name = "allgathercommimpl"
|
||||
|
||||
forward_context.moe_comm_method = getattr(self, moe_comm_method_name)
|
||||
|
||||
Reference in new issue
Block a user