[CI/Build][CPU] Fix failed pooling tests and macos smoke test (#32907)
Signed-off-by: jiang1.li <jiang1.li@intel.com> Signed-off-by: Li, Jiang <bigpyj64@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
@@ -230,7 +230,7 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, ops) {
|
||||
#endif
|
||||
|
||||
// SHM CCL
|
||||
#if defined(__AVX512F__) || defined(__aarch64__)
|
||||
#if defined(__AVX512F__) || (defined(__aarch64__) && !defined(__APPLE__))
|
||||
ops.def("init_shm_manager(str name, int group_size, int rank) -> int",
|
||||
&init_shm_manager);
|
||||
ops.def("join_shm_manager(int handle, str name) -> str", &join_shm_manager);
|
||||
|
||||
@@ -216,8 +216,14 @@ def dispatch_cpu_unquantized_gemm(
|
||||
layer: torch.nn.Module,
|
||||
remove_weight: bool,
|
||||
) -> None:
|
||||
# skip for missing layers
|
||||
if layer.weight.is_meta:
|
||||
layer.cpu_linear = torch.nn.functional.linear
|
||||
return
|
||||
|
||||
N, K = layer.weight.size()
|
||||
dtype = layer.weight.dtype
|
||||
|
||||
if envs.VLLM_CPU_SGL_KERNEL and check_cpu_sgl_kernel(N, K, dtype):
|
||||
packed_weight = torch.ops._C.convert_weight_packed(layer.weight)
|
||||
if getattr(layer, "bias", None) is not None:
|
||||
|
||||
Reference in New Issue
Block a user