[INIT] Fix fallback for unsupported user-specified runtime unroll factor (#1780)

* [INIT] Fix fallback for unsupported user-specified runtime unroll factor * Add CollTrace guard * Move `commSetUnrollFactor()` to rccl_wrap.cc * Modify comments in the device-code generator script
2025-07-10 10:56:18 -05:00
parent 68d6f99e0f
commit 2c099fe29a
6 changed files with 61 additions and 45 deletions
@@ -17,6 +17,8 @@
 #define NCCL_SIMPLE_ALIGNMENT (WARP_SIZE * 8LL * 16LL)
 #define NCCL_BYTES_ALIGNMENT 16

+void* rcclGetKernelIndex(int unroll, bool useCollTrace, struct ncclTaskColl* task = NULL);
+
 ncclResult_t ncclInitKernelsForDevice(int cudaArch, int maxSharedMem, size_t* maxStackSize);
 ncclResult_t ncclEnqueueCheck(struct ncclInfo* info);
 ncclResult_t ncclLaunchPrepare(struct ncclComm* comm);