CookieApril/enginex-ascend-910-vllm
1
0
Fork 0
forked from EngineX-Ascend/enginex-ascend-910-vllm
Code Pull Requests Activity

init v0.11.0rc0

Browse Source
This commit is contained in:
luopingyi
2025-10-14 10:38:28 +08:00
parent 67afd0ea78
commit 66dc16f966
278 changed files with 28130 additions and 11708 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/quantization/w8a8.py
View File

@@ -23,7 +23,7 @@ from vllm.attention.backends.abstract import AttentionType
from vllm.distributed.parallel_state import get_ep_group
from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.ops.layers.experts_selector import select_experts
from vllm_ascend.ops.moe.experts_selector import select_experts
from vllm_ascend.utils import ACL_FORMAT_FRACTAL_NZ, is_310p