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

19
vllm_ascend/model_loader/netloader/load.py
View File

@@ -48,36 +48,27 @@ def elastic_load(
# Filter sources for the current device
sources_this_device = []
for s in sources:
if isinstance(
s, dict
) and "device_id" in s and s["device_id"] == device_id and isinstance(
s["sources"], list):
if isinstance(s, dict) and "device_id" in s and s["device_id"] == device_id and isinstance(s["sources"], list):
sources_this_device += s["sources"]
if len(sources_this_device) == 0:
return None
try:
# Initialize the interaction layer with the ElasticClient
with ElasticClient(sources_this_device, device_id, model_path, tp,
pp) as client_interaction_layer:
with ElasticClient(sources_this_device, device_id, model_path, tp, pp) as client_interaction_layer:
if client_interaction_layer.s is None or client_interaction_layer.server_addr is None:
raise RuntimeError(
"Failed to initialize ElasticClient: socket or server_addr is None"
)
raise RuntimeError("Failed to initialize ElasticClient: socket or server_addr is None")
ack = client_interaction_layer.ack
if ack is None:
raise RuntimeError("ElasticClient.register did not return ack")
t0 = time.perf_counter()
elastic_loader = P2PLoad(ack[0],
client_interaction_layer.server_addr,
ack[1])
elastic_loader = P2PLoad(ack[0], client_interaction_layer.server_addr, ack[1])
model_loaded = elastic_loader.load(model=model)
if model_loaded is None:
logger.error("Failed to load model")
return None
logger.info("Finish elastic load (duration: {}s)".format(
time.perf_counter() - t0))
logger.info("Finish elastic load (duration: {}s)".format(time.perf_counter() - t0))
return model_loaded
except Exception as e:
logger.info(f"elastic_load error: {e}")