Skip to content

GitLab

Unverified Commit b2f915cb authored by thatPepe's avatar thatPepe Committed by GitHub
Browse files

Merge pull request #1046 from InfiniTensor/issue/1032i 

issue/1032 - fix block size on iluvatar
parents abd45713 c3946bf0
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 3 deletions
src/infiniop/ops/swiglu/nvidia/swiglu_nvidia_cuda.cu
View file @ b2f915cb
......@@ -106,10 +106,12 @@ infiniStatus_t Descriptor::calculate(
return INFINI_STATUS_BAD_TENSOR_DTYPE; \
}
if (_opaque->internal->maxThreadsPerBlock() == CUDA_BLOCK_SIZE_1024) {
CALCULATE_SWIGLU_CUDA_WITH_BLOCK_SIZE(CUDA_BLOCK_SIZE_1024)
} else if (_opaque->internal->maxThreadsPerBlock() == CUDA_BLOCK_SIZE_512) {
if (_opaque->internal->maxThreadsPerBlock() == CUDA_BLOCK_SIZE_512) {
CALCULATE_SWIGLU_CUDA_WITH_BLOCK_SIZE(CUDA_BLOCK_SIZE_512)
} else if (_opaque->internal->maxThreadsPerBlock() == CUDA_BLOCK_SIZE_1024) {
CALCULATE_SWIGLU_CUDA_WITH_BLOCK_SIZE(CUDA_BLOCK_SIZE_1024)
} else if (_opaque->internal->maxThreadsPerBlock() == CUDA_BLOCK_SIZE_2048) {
CALCULATE_SWIGLU_CUDA_WITH_BLOCK_SIZE(CUDA_BLOCK_SIZE_2048)
} else if (_opaque->internal->maxThreadsPerBlock() == CUDA_BLOCK_SIZE_4096) {
CALCULATE_SWIGLU_CUDA_WITH_BLOCK_SIZE(CUDA_BLOCK_SIZE_4096)
} else {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment