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 deep_ep.cpp

Browse Source
This commit is contained in:
fzyzcjy 2025-04-29 09:58:31 +08:00 committed by GitHub
parent 65e2a700f0
commit 23ded3bd8d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/deep_ep.cpp
View File

@ -614,6 +614,8 @@ Buffer::internode_dispatch(const torch::Tensor& x, const std::optional<torch::Te
const std::optional<torch::Tensor>& cached_rdma_channel_prefix_matrix, const std::optional<torch::Tensor>& cached_recv_rdma_rank_prefix_sum,
const std::optional<torch::Tensor>& cached_gbl_channel_prefix_matrix, const std::optional<torch::Tensor>& cached_recv_gbl_rank_prefix_sum,
int expert_alignment, const Config& config, std::optional<EventHandle>& previous_event, bool async, bool allocate_on_comm_stream) {
pybind11::gil_scoped_release release;
const int num_channels = config.num_sms / 2;
EP_HOST_ASSERT(config.num_sms % 2 == 0);
EP_HOST_ASSERT(0 < get_num_rdma_ranks() and get_num_rdma_ranks() <= NUM_MAX_RDMA_PEERS);