[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:
Rehan Khan
2026-07-31 17:49:31 +08:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent 482cfc20f0
commit 88bc8fb56f
6 changed files with 182 additions and 27 deletions
+1 -1
View File
@@ -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);