[Refactor]310p_e2e test case update (#6539)
### What this PR does / why we need it? This pull request significantly enhances the test suite by adding new end-to-end test cases for Qwen3 models on the 310P hardware platform. The primary goal is to ensure the stability and correctness of these models under diverse operational conditions, including various parallelism strategies, data types, and quantization methods. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? E2E test - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0 --------- Signed-off-by: pu-zhe <zpuaa@outlook.com>
This commit is contained in:
@@ -251,9 +251,11 @@ class AscendSharedFusedMoE310(SharedFusedMoE, AscendFusedMoE310):
|
||||
shared_experts: torch.nn.Module,
|
||||
gate: torch.nn.Module | None = None,
|
||||
use_overlapped: bool = True,
|
||||
routed_input_transform: torch.nn.Module | None = None,
|
||||
**kwargs,
|
||||
):
|
||||
AscendFusedMoE310.__init__(self, **kwargs)
|
||||
self._routed_input_transform = routed_input_transform
|
||||
self._shared_experts = shared_experts
|
||||
self.use_overlapped = use_overlapped
|
||||
self.shared_expert_stream = None
|
||||
|
||||
@@ -25,9 +25,7 @@ from vllm_ascend.worker.worker import NPUWorker, init_workspace_manager
|
||||
class NPUWorker310(NPUWorker):
|
||||
def init_device(self):
|
||||
self.device = self._init_device()
|
||||
|
||||
# TODO: There is accuracy issue when jit_compile is disabled currently.
|
||||
torch_npu.npu.set_compile_mode(jit_compile=True)
|
||||
torch_npu.npu.set_compile_mode(jit_compile=False)
|
||||
|
||||
init_workspace_manager(self.device, num_ubatches=1)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user