biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Fix some narrowing conversion warnings (#20141)

Browse Source 
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
This commit is contained in:
Tyler Michael Smith
2025-06-27 12:01:28 -04:00
committed by GitHub
parent c6c983053d
commit e8c3bd2cd1
6 changed files with 8 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/attention/mla/cutlass_mla_kernels.cu
View File

@@ -207,7 +207,7 @@ void cutlass_mla_decode_sm100a(torch::Tensor const& out,
"page_table must be a 32-bit integer tensor");
auto in_dtype = q_nope.dtype();
at::cuda::CUDAGuard device_guard{(char)q_nope.get_device()};
const at::cuda::OptionalCUDAGuard device_guard(device_of(q_nope));
const cudaStream_t stream =
at::cuda::getCurrentCUDAStream(q_nope.get_device());
if (in_dtype == at::ScalarType::Half) {