[CPU][INT4] Add INT4 kernels for CPU (#8226)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
jianan-gu
2026-01-29 22:30:13 -08:00
committed by GitHub
co-authored by gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
parent 88f7759402
commit c35aa0238c
14 changed files with 1769 additions and 72 deletions
-2
View File
@@ -742,8 +742,6 @@ class DeepseekV2MoE(nn.Module):
if self.shared_experts_is_fp8
else None
), # block_size
None, # a1_scale
None, # a2_scale
True, # is_vnni
)
if self.tp_size > 1 and not should_allreduce_fusion: