huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-16 18:48:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into conv-transpose-groups

Browse Source
This commit is contained in:
laurent
2023-09-09 18:50:13 +01:00
parent b4fe316fa1 258ac32c38
commit b283b3e181
2 changed files with 18 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
candle-core/src/cuda_backend.rs
View File

@ -312,6 +312,13 @@ impl BackendDevice for CudaDevice {
// cudarc changes.
let elem_count = shape.elem_count();
let curand = self.curand.lock().unwrap();
// curand can only generate an odd number of values.
// https://github.com/huggingface/candle/issues/734
let elem_count_round = if elem_count % 2 == 1 {
elem_count + 1
} else {
elem_count
};
let slice = match dtype {
DType::U8 | DType::U32 | DType::I64 | DType::F16 | DType::BF16 => {
Err(CudaError::UnsupportedDtype {
@ -321,7 +328,7 @@ impl BackendDevice for CudaDevice {
.w()?
}
DType::F32 => {
let mut data = unsafe { self.alloc::<f32>(elem_count) }.w()?;
let mut data = unsafe { self.alloc::<f32>(elem_count_round) }.w()?;
curand
.0
.fill_with_normal(&mut data, mean as f32, std as f32)
@ -329,7 +336,7 @@ impl BackendDevice for CudaDevice {
CudaStorageSlice::F32(data)
}
DType::F64 => {
let mut data = unsafe { self.alloc::<f64>(elem_count) }.w()?;
let mut data = unsafe { self.alloc::<f64>(elem_count_round) }.w()?;
curand.0.fill_with_normal(&mut data, mean, std).w()?;
CudaStorageSlice::F64(data)
}

9
candle-core/tests/tensor_tests.rs
View File

@ -877,6 +877,14 @@ fn broadcasting(device: &Device) -> Result<()> {
Ok(())
}
fn randn(device: &Device) -> Result<()> {
let tensor = Tensor::randn(0f32, 1f32, (5, 3), device)?;
assert_eq!(tensor.dims(), [5, 3]);
let tensor = Tensor::rand(0f32, 1f32, (5, 3), device)?;
assert_eq!(tensor.dims(), [5, 3]);
Ok(())
}
test_device!(zeros, zeros_cpu, zeros_gpu);
test_device!(add_mul, add_mul_cpu, add_mul_gpu);
test_device!(tensor_2d, tensor_2d_cpu, tensor_2d_gpu);
@ -899,6 +907,7 @@ test_device!(index_select, index_select_cpu, index_select_gpu);
test_device!(index_add, index_add_cpu, index_add_gpu);
test_device!(gather, gather_cpu, gather_gpu);
test_device!(scatter_add, scatter_add_cpu, scatter_add_gpu);
test_device!(randn, randn_cpu, randn_gpu);
// There was originally a bug on the CPU implementation for randn
// https://github.com/huggingface/candle/issues/381