leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 24 Packages Projects Releases Wiki Activity

Updates for 3.4 release. (#1305)

Browse Source
This commit is contained in:
ANIKET SHIVAM
2024-01-16 13:42:51 -05:00
committed by GitHub
parent acba5beee5
commit 2f589ffa76
166 changed files with 5996 additions and 4702 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/cutlass/gemm/kernel/gemv_batched_strided.h
+3 -3
View File
@@ -186,7 +186,7 @@ CUTLASS_DEVICE void GemvBatchedStridedDevice(
}
template <typename GemvKernel, typename ElementAlphaBeta, bool BetaIsZero>
__global__ void GemvBatchedStrided(
CUTLASS_GLOBAL void GemvBatchedStrided(
cutlass::gemm::BatchedGemmCoord problem_size,
ElementAlphaBeta alpha,
ElementAlphaBeta beta,
@@ -205,7 +205,7 @@ __global__ void GemvBatchedStrided(
}
template <typename GemvKernel, typename ElementAlphaBeta>
__global__ void GemvBatchedStrided(
CUTLASS_GLOBAL void GemvBatchedStrided(
cutlass::gemm::BatchedGemmCoord problem_size,
ElementAlphaBeta alpha,
typename GemvKernel::IteratorA::TensorRef ref_A,
@@ -221,7 +221,7 @@ __global__ void GemvBatchedStrided(
}
template <typename GemvKernel>
__global__ void GemvBatchedStrided(
CUTLASS_GLOBAL void GemvBatchedStrided(
cutlass::gemm::BatchedGemmCoord problem_size,
typename GemvKernel::IteratorA::TensorRef ref_A,
typename GemvKernel::IteratorA::TensorRef::LongIndex lda,