Stop setting CUDA_VISIBLE_DEVICES internally in vLLM, add device_ids arg (#45026)

Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: kourosh hakhamaneshi <kouroshHakha@users.noreply.github.com>
This commit is contained in:
Tyler Michael Smith
2026-06-20 13:38:10 -07:00
committed by GitHub
co-authored by Claude Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> kourosh hakhamaneshi
parent e9de72fe6c
commit ebfbcfe46a
24 changed files with 722 additions and 185 deletions
@@ -268,9 +268,14 @@ int64_t sm100_cutlass_mla_get_workspace_size(int64_t max_seq_len, int64_t num_ba
using TileShapeD = typename MlaSm100Type::TileShapeD;
arguments.problem_shape =
cute::make_tuple(TileShapeH{}, static_cast<int>(max_seq_len), TileShapeD{}, static_cast<int>(num_batches));
// Assumes device 0 when getting sm_count.
arguments.hw_info.sm_count =
sm_count <= 0 ? cutlass::KernelHardwareInfo::query_device_multiprocessor_count(/*device_id=*/0) : sm_count;
if (sm_count <= 0) {
int current_device = 0;
cudaGetDevice(&current_device);
arguments.hw_info.sm_count =
cutlass::KernelHardwareInfo::query_device_multiprocessor_count(current_device);
} else {
arguments.hw_info.sm_count = sm_count;
}
arguments.split_kv = static_cast<int>(num_kv_splits);
MlaSm100Type::Fmha::set_split_kv(arguments);