karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity

[XPU] support HND layout (#47975)

Browse Source 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
This commit is contained in:
liuzhenwei
2026-07-17 10:54:34 +00:00
committed by GitHub
parent ce4bdcbda4
commit 8502958810
1 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
vllm/platforms/xpu.py
-8
View File
@@ -124,14 +124,6 @@ class XPUPlatform(Platform):
attn_selector_config: "AttentionSelectorConfig",
num_heads: int | None = None,
) -> str:
from vllm.v1.attention.backends.utils import set_kv_cache_layout
set_kv_cache_layout("NHD")
logger.info_once(
"Setting VLLM_KV_CACHE_LAYOUT to 'NHD' for XPU; "
"only NHD layout is supported by XPU attention kernels."
)
# TurboQuant KV cache: route directly to TQ backend
kv_cache_dtype = attn_selector_config.kv_cache_dtype
if kv_cache_dtype is not None and kv_cache_dtype.startswith("turboquant_"):