biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Hardware][Intel GPU] Upgrade to torch 2.7 (#17444)

Browse Source 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Qiming Zhang <qiming1.zhang@intel.com>
This commit is contained in:
Kunshang Ji
2025-04-30 15:03:58 +08:00
committed by GitHub
parent 6ed9f6047e
commit ed6cfb90c8
5 changed files with 18 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
vllm/_ipex_ops.py
View File

@@ -177,6 +177,7 @@ class ipex_ops:
out: torch.Tensor,
seqlen_q: torch.Tensor,
seqlen_k: torch.Tensor,
alibi_slopes: torch.Tensor,
max_seqlen_q: int,
max_seqlen_k: int,
pdropout: float,
@@ -185,6 +186,8 @@ class ipex_ops:
is_causal: bool,
return_softmax: bool,
gen_: torch.Generator,
window_size_left: float,
window_size_right: float,
logits_soft_cap: float,
) -> None:
if ipex.__version__.endswith("cpu"):
@@ -200,15 +203,12 @@ class ipex_ops:
is_causal, return_softmax,
gen_)
else: # XPU build
ipex.llm.functional.varlen_attention(query.contiguous(),
key.contiguous(),
value.contiguous(), out,
seqlen_q.int(),
seqlen_k.int(), max_seqlen_q,
max_seqlen_k, pdropout,
softmax_scale, zero_tensors,
is_causal, return_softmax,
gen_, logits_soft_cap)
ipex.llm.functional.varlen_attention(
query.contiguous(), key.contiguous(), value.contiguous(), out,
seqlen_q.int(), seqlen_k.int(), alibi_slopes, max_seqlen_q,
max_seqlen_k, pdropout, softmax_scale, zero_tensors, is_causal,
return_softmax, gen_, window_size_left, window_size_right,
logits_soft_cap)
@staticmethod
def reshape_and_cache(