xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 06:35:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix pre-commit (and XPU) on main (#28556)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor 2025-11-12 14:13:41 +00:00 committed by GitHub
parent 10138c92a5
commit 54aecd9ed5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/mxfp4.py
View File

@ -1145,7 +1145,7 @@ class IpexMxfp4MoEMethod(Mxfp4MoEMethod):
) -> torch.Tensor:
assert activation == "swigluoai", (
"Only swiglu_oai activation is supported for IPEX MXFP4 MoE"
) # noqa:
)
hidden_size_pad = round_up(self.original_hidden_size, 128)
x_pad = torch.nn.functional.pad(x, (0, hidden_size_pad - x.size(-1)))
hidden_states = layer.ipex_fusion(

2
vllm/platforms/xpu.py
View File

@ -64,8 +64,6 @@ class XPUPlatform(Platform):
if use_sparse:
raise NotImplementedError("Sparse Attention is not supported on XPU.")
if not use_v1:
raise ValueError("XPU backend only supports V1.")
if selected_backend == AttentionBackendEnum.TRITON_ATTN:
logger.info_once("Using Triton backend.")
return AttentionBackendEnum.TRITON_ATTN.get_path()