refactor: add a check before layer_sharding logging (#7186)
### What this PR does / why we need it? We should only display this log message when layer_sharding is enabled. - vLLM version: v0.16.0 - vLLM main: https://github.com/vllm-project/vllm/commit/4034c3d32e30d01639459edd3ab486f56993876d Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
This commit is contained in:
1 file changed
+6
-5
@@ -52,11 +52,12 @@ class AscendConfig:
|
||||
self.dump_config_path = additional_config.get("dump_config_path", None)
|
||||
self._construct_weight_prefetch_config(additional_config)
|
||||
self.layer_sharding = additional_config.get("layer_sharding", None)
|
||||
logger.info_once(
|
||||
f"Linear layer sharding enabled with config: {self.layer_sharding}. "
|
||||
"Note: This feature works optimally with FLASHCOMM2 and DSA-CP enabled; "
|
||||
"using it without these features may result in significant performance degradation."
|
||||
)
|
||||
if self.layer_sharding:
|
||||
logger.info_once(
|
||||
f"Linear layer sharding enabled with config: {self.layer_sharding}. "
|
||||
"Note: This feature works optimally with FLASHCOMM2 and DSA-CP enabled; "
|
||||
"using it without these features may result in significant performance degradation."
|
||||
)
|
||||
|
||||
self.enable_shared_expert_dp = (
|
||||
additional_config.get("enable_shared_expert_dp", False)
|
||||
|
||||
Reference in new issue
Block a user