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

Bugs fixed

Browse Source
This commit is contained in:
Chenggang Zhao
2025-03-05 14:27:45 +08:00
parent 592296cd45
commit 680e424bdc
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/kernels/internode.cu
View File

@@ -383,8 +383,7 @@ notify_dispatch(const int* num_tokens_per_rank, int* moe_recv_counter_mapped, in
// Calculate prefix sum
__syncthreads();
EP_STATIC_ASSERT(kNumRDMARanks <= 32, "Invalid number of RDMA ranks");
if (thread_id < kNumRDMARanks) {
if (thread_id == 0) {
auto prefix_row = rdma_channel_prefix_matrix + dst_rdma_rank * num_channels;
#pragma unroll
for (int i = 1; i < num_channels; ++ i)