[CPU][s390x] Optimize inference perf and add oneDNN INT8 GEMM for s390x (#50219)
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com> Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
co-authored by
Li, Jiang <jiang1.li@intel.com>
parent
482cfc20f0
commit
88bc8fb56f
@@ -398,7 +398,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
// Quantization
|
||||
#if defined(__AVX512F__) || defined(__AVX2__) || \
|
||||
(defined(__aarch64__) && !defined(__APPLE__)) || defined(__powerpc64__) || \
|
||||
defined(__riscv_v)
|
||||
defined(__riscv_v) || defined(__s390x__)
|
||||
// Helper function to release oneDNN handlers
|
||||
ops.def("release_dnnl_matmul_handler(int handler) -> ()",
|
||||
&release_dnnl_matmul_handler);
|
||||
|
||||
Reference in New Issue
Block a user