[Feature] Integrate Elastic NIXL-EP into SGLang (#19248)

Signed-off-by: Barak Biber <bbiber@nvidia.com>
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Co-authored-by: Barak Biber <bbiber@nvidia.com>
This commit is contained in:
Yoray Zack
2026-03-11 17:37:43 +08:00
committed by GitHub
co-authored by Barak Biber
parent 680d9d98e4
commit 9991debde3
18 changed files with 752 additions and 17 deletions
+3
View File
@@ -445,6 +445,7 @@ class DeepseekV2MoE(nn.Module):
dict(tp_rank=0, tp_size=1)
if get_moe_a2a_backend().is_deepep()
or get_moe_a2a_backend().is_mooncake()
or get_moe_a2a_backend().is_nixl()
or get_moe_a2a_backend().is_mori()
or get_moe_a2a_backend().is_ascend_fuseep()
or get_moe_a2a_backend().is_flashinfer()
@@ -489,6 +490,7 @@ class DeepseekV2MoE(nn.Module):
if (
get_moe_a2a_backend().is_deepep()
or get_moe_a2a_backend().is_mooncake()
or get_moe_a2a_backend().is_nixl()
or get_moe_a2a_backend().is_mori()
or get_moe_a2a_backend().is_ascend_fuseep()
):
@@ -510,6 +512,7 @@ class DeepseekV2MoE(nn.Module):
self._enable_a2a_moe = (
get_moe_a2a_backend().is_deepep()
or get_moe_a2a_backend().is_mooncake()
or get_moe_a2a_backend().is_nixl()
or get_moe_a2a_backend().is_mori()
or get_moe_a2a_backend().is_ascend_fuseep()
or get_moe_a2a_backend().is_flashinfer()