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

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #6) (#6001)

Browse Source 
### What this PR does / why we need it?
| File Path |
| :--- |
| ` vllm_ascend/eplb/adaptor/abstract_adaptor.py` |
| ` vllm_ascend/eplb/adaptor/vllm_adaptor.py` |
| ` vllm_ascend/eplb/core/eplb_device_transfer_loader.py` |
| ` vllm_ascend/eplb/core/eplb_utils.py` |
| ` vllm_ascend/eplb/core/eplb_worker.py` |
| ` vllm_ascend/eplb/core/policy/policy_abstract.py` |
| ` vllm_ascend/eplb/core/policy/policy_default_eplb.py` |
| ` vllm_ascend/eplb/core/policy/policy_factory.py` |
| ` vllm_ascend/eplb/core/policy/policy_flashlb.py` |
| ` vllm_ascend/eplb/core/policy/policy_random.py` |
| ` vllm_ascend/eplb/core/policy/policy_swift_balancer.py` |
| ` vllm_ascend/eplb/eplb_updator.py` |
| ` vllm_ascend/eplb/utils.py` |
| ` vllm_ascend/model_loader/netloader/executor/elastic_load.py` |
| ` vllm_ascend/model_loader/netloader/executor/netloader_pg.py` |
| ` vllm_ascend/model_loader/netloader/interaction/elastic.py` |
| ` vllm_ascend/model_loader/netloader/load.py` |
| ` vllm_ascend/model_loader/netloader/netloader.py` |
| ` vllm_ascend/model_loader/netloader/utils.py` |
| ` vllm_ascend/patch/platform/__init__.py` |
| ` vllm_ascend/patch/platform/patch_balance_schedule.py` |
| ` vllm_ascend/patch/platform/patch_ec_connector.py` |
| ` vllm_ascend/patch/platform/patch_mamba_config.py` |
| ` vllm_ascend/patch/platform/patch_multiproc_executor.py` |
| ` vllm_ascend/patch/platform/patch_sched_yield.py` |


- vLLM version: v0.13.0
- vLLM main:
2c24bc6996

---------

Signed-off-by: MrZ20 <2609716663@qq.com>
This commit is contained in:
SILONG ZENG
2026-01-24 22:08:33 +08:00
committed by GitHub
parent 153da1a669
commit 4e53c1d900
26 changed files with 894 additions and 1148 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
vllm_ascend/eplb/utils.py
View File

@@ -30,33 +30,30 @@ def get_log2phy_map(self, layer_id):
def get_all_expert_map(self, num_moe_layers):
all_loads = []
num_dense_layers = self.num_dense_layers if hasattr(
self, "num_dense_layers") else 0
num_dense_layers = self.num_dense_layers if hasattr(self, "num_dense_layers") else 0
for layer_id in range(num_moe_layers):
load_tensor = self.get_expert_map(
layer_id + num_dense_layers) # (num_experts_per_layer,)
load_tensor = self.get_expert_map(layer_id + num_dense_layers) # (num_experts_per_layer,)
all_loads.append(load_tensor)
return torch.stack(all_loads, dim=0)
def get_all_moe_loads(self):
num_dense_layers = self.num_dense_layers if hasattr(
self, "num_dense_layers") else 0
num_dense_layers = self.num_dense_layers if hasattr(self, "num_dense_layers") else 0
all_moe_loads = torch.stack(
[self.model.layers[layer_id + num_dense_layers].mlp.experts.moe_load \
for layer_id in range(self.num_moe_layers)],
dim=0
[
self.model.layers[layer_id + num_dense_layers].mlp.experts.moe_load
for layer_id in range(self.num_moe_layers)
],
dim=0,
)
return all_moe_loads
def clear_all_moe_loads(self):
num_dense_layers = self.num_dense_layers if hasattr(
self, "num_dense_layers") else 0
num_dense_layers = self.num_dense_layers if hasattr(self, "num_dense_layers") else 0
for layer_id in range(self.num_moe_layers):
self.model.layers[layer_id +
num_dense_layers].mlp.experts.clear_moe_load()
self.model.layers[layer_id + num_dense_layers].mlp.experts.clear_moe_load()
def model_register(model, model_config):