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

fix(cpu): fix mla_decode compilation on x86 without AVX512 (#34052)

Browse Source 
Signed-off-by: ihb2032 <hebome@foxmail.com>
Co-authored-by: root <root@LAPTOP-FKNHV411.localdomain>
This commit is contained in:
ihb2032
2026-02-09 16:55:41 +08:00
committed by GitHub
parent d9bede0314
commit 5a5c43511a
1 changed files with 1 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
csrc/cpu/mla_decode.cpp
View File

@@ -38,16 +38,7 @@ struct KernelVecType<c10::BFloat16> {
using qk_vec_type = vec_op::BF16Vec32;
using v_load_vec_type = vec_op::BF16Vec16;
};
#elif defined(__s390x__)
template <>
struct KernelVecType<c10::BFloat16> {
using qk_load_vec_type = vec_op::BF16Vec16;
using qk_vec_type = vec_op::FP32Vec16;
using v_load_vec_type = vec_op::BF16Vec16;
};
#elif defined(__aarch64__)
#else
template <>
struct KernelVecType<c10::BFloat16> {
using qk_load_vec_type = vec_op::BF16Vec16;