mirror of
https://github.com/ml-explore/mlx.git
synced 2025-12-16 01:49:05 +08:00
[CUDA] Reduce use of managed memory (#2725)
Some checks failed
Nightly Build / build_linux_release (3.10) (push) Has been cancelled
Nightly Build / build_linux_release (3.14) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.10) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.11) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.12) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.13) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.14) (push) Has been cancelled
Nightly Build / build_mac_release (3.10) (push) Has been cancelled
Nightly Build / build_mac_release (3.13) (push) Has been cancelled
Nightly Build / build_cuda_with_tests (push) Has been cancelled
Nightly Build / build_cuda_release (push) Has been cancelled
Nightly Build / Linux Fedora CPP Build (aarch64) (push) Has been cancelled
Nightly Build / Linux Fedora CPP Build (x86_64) (push) Has been cancelled
Some checks failed
Nightly Build / build_linux_release (3.10) (push) Has been cancelled
Nightly Build / build_linux_release (3.14) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.10) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.11) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.12) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.13) (push) Has been cancelled
Nightly Build / build_linux_with_tests (3.14) (push) Has been cancelled
Nightly Build / build_mac_release (3.10) (push) Has been cancelled
Nightly Build / build_mac_release (3.13) (push) Has been cancelled
Nightly Build / build_cuda_with_tests (push) Has been cancelled
Nightly Build / build_cuda_release (push) Has been cancelled
Nightly Build / Linux Fedora CPP Build (aarch64) (push) Has been cancelled
Nightly Build / Linux Fedora CPP Build (x86_64) (push) Has been cancelled
* Use async cuda malloc managed with cuda 13 * add pool threshold * refactor for regular cuda malloc * load eval gpu for cuda * remove use of cuda pool, use cuda free async * fix * fix * fix * fix * fix + comment
This commit is contained in:
@@ -333,7 +333,7 @@ void Reshape::eval_cpu(const std::vector<array>& inputs, array& out) {
|
||||
|
||||
void DynamicSlice::eval_cpu(const std::vector<array>& inputs, array& out) {
|
||||
if (out.size() == 0) {
|
||||
out.set_data(nullptr);
|
||||
out.set_data(allocator::malloc(0));
|
||||
return;
|
||||
}
|
||||
auto& in = inputs[0];
|
||||
@@ -361,7 +361,7 @@ void DynamicSliceUpdate::eval_cpu(
|
||||
const std::vector<array>& inputs,
|
||||
array& out) {
|
||||
if (out.size() == 0) {
|
||||
out.set_data(nullptr);
|
||||
out.set_data(allocator::malloc(0));
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -396,7 +396,7 @@ void DynamicSliceUpdate::eval_cpu(
|
||||
void SliceUpdate::eval_cpu(const std::vector<array>& inputs, array& out) {
|
||||
assert(inputs.size() == 2);
|
||||
if (out.size() == 0) {
|
||||
out.set_data(nullptr);
|
||||
out.set_data(allocator::malloc(0));
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user