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

7
csrc/cpu/quant.cpp
View File

@@ -23,6 +23,13 @@ struct KernelVecType<c10::BFloat16> {
using cvt_vec_type = vec_op::FP32Vec16;
};
template <>
struct KernelVecType<c10::Half> {
using load_vec_type = vec_op::FP16Vec16;
using azp_adj_load_vec_type = vec_op::INT32Vec16;
using cvt_vec_type = vec_op::FP32Vec16;
};
#ifdef __AVX512F__
template <bool AZP, typename scalar_t>
void static_scaled_int8_quant_impl(const scalar_t* input, int8_t* output,