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

Add fast-debugging flags

Browse Source
This commit is contained in:
Chenggang Zhao
2025-06-23 11:47:51 +08:00
parent 1c277c303e
commit 6a708ec14c
4 changed files with 9 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
csrc/kernels/configs.cuh
View File

@@ -7,9 +7,15 @@
#define NUM_BUFFER_ALIGNMENT_BYTES 128
#define FINISHED_SUM_TAG 1024
#define NUM_WAIT_NANOSECONDS 500
#ifndef ENABLE_FAST_DEBUG
#define NUM_CPU_TIMEOUT_SECS 100
#define NUM_TIMEOUT_CYCLES 200000000000ull // 200G cycles ~= 100s
#define NUM_WAIT_NANOSECONDS 500
#else
#define NUM_CPU_TIMEOUT_SECS 10
#define NUM_TIMEOUT_CYCLES 20000000000ull // 20G cycles ~= 10s
#endif
#define LOW_LATENCY_SEND_PHASE 1
#define LOW_LATENCY_RECV_PHASE 2

4
csrc/kernels/launch.cuh
View File

@@ -58,12 +58,9 @@ cfg.dynamicSmemBytes = smem_size;
#define SWITCH_RDMA_RANKS(case_macro) \
switch (num_ranks / NUM_MAX_NVL_PEERS) { \
case 2: case_macro(2); \
case 3: case_macro(3); \
case 4: case_macro(4); \
case 8: case_macro(8); \
case 16: case_macro(16); \
case 18: case_macro(18); \
case 20: case_macro(20); \
default: EP_HOST_ASSERT(false and "Unsupported RDMA ranks"); \
} while (false)
@@ -78,7 +75,6 @@ cfg.dynamicSmemBytes = smem_size;
#define SWITCH_TYPES(case_macro) \
switch (type) { \
case CUDA_R_16BF: case_macro(nv_bfloat16); \
case CUDA_R_32F: case_macro(float); \
default: EP_HOST_ASSERT(false && "Unsupported type"); \
} while (false)