apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Feature] Support redundant expert for eplb (#5918)

Browse Source 
* [BugFix] support redundant expert for eplb

* support redundant expert for eplb

* support redundant expert for eplb

* update

* fix ci eplb
This commit is contained in:
xiaoxiaohehe001
2026-01-09 17:13:24 +08:00
committed by GitHub
parent e6cdea4492
commit 00a01ae024
11 changed files with 36 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/gpu_ops/moe/ep_moe_expert_dispatch.cu
+10
View File
@@ -48,6 +48,11 @@
__VA_ARGS__ \
break; \
} \
case 7: { \
constexpr size_t NUM_EXPERTS_PER_RANK = 7; \
__VA_ARGS__ \
break; \
} \
case 8: { \
constexpr size_t NUM_EXPERTS_PER_RANK = 8; \
__VA_ARGS__ \
@@ -68,6 +73,11 @@
__VA_ARGS__ \
break; \
} \
case 17: { \
constexpr size_t NUM_EXPERTS_PER_RANK = 17; \
__VA_ARGS__ \
break; \
} \
case 20: { \
constexpr size_t NUM_EXPERTS_PER_RANK = 20; \
__VA_ARGS__ \