mirror of
https://github.com/deepseek-ai/DeepEP
synced 2025-06-26 18:28:11 +00:00
Support statistics tensor for low-latency kernels (#196)
This commit is contained in:
@@ -133,6 +133,7 @@ void clean_low_latency_buffer(int* clean_0, int num_clean_int_0,
|
||||
void dispatch(void* packed_recv_x, float* packed_recv_x_scales,
|
||||
int* packed_recv_src_info, int64_t* packed_recv_layout_range,
|
||||
int* packed_recv_count,
|
||||
int* cumulative_local_expert_recv_stats,
|
||||
void* rdma_recv_x, int* rdma_recv_count, void* rdma_x,
|
||||
const void* x, const int64_t* topk_idx,
|
||||
int* next_clean, int num_next_clean_int,
|
||||
|
||||
Reference in New Issue
Block a user