DeepSeek/DeepEP
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepEP synced 2025-06-26 18:28:11 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix AR bugs for normal kernels

Browse Source
This commit is contained in:
Chenggang Zhao
2025-03-05 17:13:35 +08:00
parent 680e424bdc
commit 458cdcb22a
5 changed files with 17 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
csrc/kernels/ibgda_device.cuh
View File

@@ -372,7 +372,6 @@ nvshmemi_ibgda_allocate_recvs(nvshmemi_ibgda_device_qp* qp) {
__device__ static __forceinline__ void
nvshmemi_ibgda_prepare_recvs(int dst_rank, int qp_id) {
// NOTES: only one thread can run this function
// TODO: consider this assertion for normal AR
EP_DEVICE_ASSERT(nvshmemi_ibgda_allocate_recvs(ibgda_get_rc(dst_rank, qp_id)) > 16);
}