EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

upgrade main to 0212 (#6712)

Browse Source 
### What this PR does / why we need it?
Fixes `transformers_utils/processors/__init__` import error, due to
https://github.com/vllm-project/vllm/pull/33247
Fixes Fused MoE break introduced by `MoERunner abstraction,` due to
https://github.com/vllm-project/vllm/pull/32344

> delete AscendMoERunnere when
https://github.com/vllm-project/vllm/pull/35178 is merged

Fixes `Make Qwen3VL compatible with Transformers v5`, due to
https://github.com/vllm-project/vllm/pull/34262

### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.15.0
- vLLM main:
9562912cea

---------

Signed-off-by: wxsIcey <1790571317@qq.com>
This commit is contained in:
Icey
2026-02-25 09:17:29 +08:00
committed by GitHub
parent 0331f16a50
commit ee59429015
11 changed files with 167 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
tests/ut/eplb/core/test_eplb_utils.py
View File

@@ -25,22 +25,35 @@ class TestAscendConfig(unittest.TestCase):
if vllm_version_is("0.15.0"):
moe_parallel_config = FusedMoEParallelConfig(
2, 0, 1, 2, 1, 1, 1, 1, True, "hccl", enable_eplb=True)
moe_config = FusedMoEConfig(
num_experts=8,
experts_per_token=8,
hidden_dim=8192,
intermediate_size_per_partition=5,
num_local_experts=8,
activation="silu",
device="npu",
routing_method=RoutingMethodType.Simulated,
moe_parallel_config=moe_parallel_config,
in_dtype=torch.float16,
)
else:
moe_parallel_config = FusedMoEParallelConfig(
2, 0, 1, 2, 1, 1, 1, 1, True, "hccl",
is_sequence_parallel=False, enable_eplb=True)
moe_config = FusedMoEConfig(
num_experts=8,
experts_per_token=8,
hidden_dim=8192,
intermediate_size_per_partition=5,
num_local_experts=8,
activation="silu",
device="npu",
routing_method=RoutingMethodType.Simulated,
moe_parallel_config=moe_parallel_config,
in_dtype=torch.float16,
)
2, 0, 1, 2, 1, 1, 1, 1, 1, True, "hccl",
enable_eplb=True)
moe_config = FusedMoEConfig(
num_experts=8,
experts_per_token=8,
hidden_dim=8192,
intermediate_size_per_partition=5,
num_local_experts=8,
num_logical_experts=8,
activation="silu",
device="npu",
routing_method=RoutingMethodType.Simulated,
moe_parallel_config=moe_parallel_config,
in_dtype=torch.float16,
)
moe_config.supports_eplb = True
self.vllm_config = vllm_config
self.moe_config = moe_config