[MoE Refactor] Remove MoE DP chunking (#39107)

Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
bnellnm
2026-04-14 09:48:05 -04:00
committed by GitHub
co-authored by Robert Shaw
parent f7e62e3d66
commit e1e318af01
20 changed files with 76 additions and 389 deletions
@@ -1502,9 +1502,9 @@ class QuarkOCP_MX_MoEMethod_OSS(QuarkOCP_MX_MoEMethod):
layer.w2_bias = torch.nn.Parameter(w2_bias, requires_grad=False)
# FIXME warp need to be adjusted based on batch size
# only apply to batched mode
# only apply to batched mode
if self.moe.use_ep:
num_warps = 4 if envs.VLLM_MOE_DP_CHUNK_SIZE <= 512 else 8
num_warps = 4 if self.moe.max_num_tokens <= 512 else 8
else:
num_warps = 8