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

[Hardware][CPU] Update torch 2.5 (#9911)

Browse Source 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2024-11-07 12:43:08 +08:00
committed by GitHub
parent 29862b884b
commit a4b3e0c1e9
12 changed files with 81 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
csrc/cpu/attention.cpp
View File

@@ -22,6 +22,16 @@ struct KernelVecType<float> {
using v_load_vec_type = vec_op::FP32Vec16;
};
template <>
struct KernelVecType<c10::Half> {
using q_load_vec_type = vec_op::FP16Vec8;
using q_vec_type = vec_op::FP32Vec16;
using k_load_vec_type = vec_op::FP16Vec16;
using k_vec_type = vec_op::FP32Vec16;
using qk_acc_vec_type = vec_op::FP32Vec16;
using v_load_vec_type = vec_op::FP16Vec16;
};
#ifdef __AVX512BF16__
template <>
struct KernelVecType<c10::BFloat16> {