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

[0.11.0]Chery pick pta upgrade change (#3940)

Browse Source 
This PR cherry-pick two commit from main to upgrade torch-npu to 2.7.1
official release

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-10-31 22:14:26 +08:00
committed by GitHub
parent 3d81ea03ed
commit 8a7154001e
16 changed files with 93 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
vllm_ascend/utils.py
View File

@@ -510,8 +510,7 @@ def register_ascend_customop(vllm_config: Optional[VllmConfig] = None):
from vllm_ascend.ops.activation import AscendQuickGELU, AscendSiluAndMul
from vllm_ascend.ops.common_fused_moe import (AscendFusedMoE,
AscendSharedFusedMoE)
from vllm_ascend.ops.layernorm import (AscendGemmaRMSNorm,
AscendQuantRMSNorm, AscendRMSNorm)
from vllm_ascend.ops.layernorm import AscendGemmaRMSNorm, AscendRMSNorm
from vllm_ascend.ops.linear import (AscendColumnParallelLinear,
AscendMergedColumnParallelLinear,
AscendQKVParallelLinear,
@@ -547,12 +546,6 @@ def register_ascend_customop(vllm_config: Optional[VllmConfig] = None):
"MultiHeadLatentAttention": AscendMultiHeadLatentAttention,
}
if vllm_config is not None and \
vllm_config.quant_config is not None and \
any("norm.bias" in name for name in vllm_config.quant_config.quant_description.keys()) and \
not version_check():
REGISTERED_ASCEND_OPS["RMSNorm"] = AscendQuantRMSNorm
for name, op_cls in REGISTERED_ASCEND_OPS.items():
CustomOp.register_oot(_decorated_op_cls=op_cls, name=name)
@@ -743,21 +736,6 @@ def is_hierarchical_communication_enabled():
and os.getenv("HCCL_INTRA_PCIE_ENABLE", "") == "1")
@functools.cache
def version_check():
"""check if torch_npu version >= dev20250919"""
import re
torch_npu_version = torch_npu.version.__version__
date_pattern = r'dev(\d{8})'
match = re.search(date_pattern, torch_npu_version)
if match:
full_date = match.group(1)
if full_date >= "20250919":
return True
return False
def has_layer_idx(model_instance: torch.nn.Module) -> bool:
if model_instance is None:
return False