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

Update intranode.cu (#210)

Browse Source
This commit is contained in:
fzyzcjy 2025-06-16 11:03:58 +08:00 committed by GitHub
parent 483f00af84
commit 4e923188f7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/kernels/intranode.cu
View File

@ -379,7 +379,7 @@ dispatch(int4* recv_x, float* recv_x_scales, int* recv_src_idx, int64_t* recv_to
while (num_tokens_to_recv > 0) { while (num_tokens_to_recv > 0) {
// NOTES: unlike the sender, the receiver must ensure that the tail indices hold by different warps are the same // NOTES: unlike the sender, the receiver must ensure that the tail indices hold by different warps are the same
while (recv_thread_id_in_rank == 0) { while (recv_thread_id_in_rank == 0) {
cached_channel_tail_idx = ld_acquire_sys_global(channel_tail_idx.buffer());; cached_channel_tail_idx = ld_acquire_sys_global(channel_tail_idx.buffer());
// Ready to copy // Ready to copy
if (cached_channel_head_idx != cached_channel_tail_idx) { if (cached_channel_head_idx != cached_channel_tail_idx) {