gahow/xserv
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: format Rust workspace

Browse Source
This commit is contained in:
Gahow Wang
2026-06-18 18:11:58 +08:00
parent 013465fc06
commit 531cd3fe08
57 changed files with 4045 additions and 1204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
crates/xserv-kernels/src/rmsnorm.rs
View File

@@ -2,13 +2,35 @@ use std::ffi::c_void;
use xserv_tensor::{DType, Device, Tensor};
unsafe extern "C" {
fn launch_rmsnorm_f32(x: *const c_void, gamma: *const c_void, out: *mut c_void,
rows: i32, hidden_size: i32, eps: f32, stream: *mut c_void);
fn launch_rmsnorm_bf16(x: *const c_void, gamma: *const c_void, out: *mut c_void,
rows: i32, hidden_size: i32, eps: f32, stream: *mut c_void);
fn launch_add_rmsnorm_bf16(x: *const c_void, residual: *const c_void, gamma: *const c_void,
normed_out: *mut c_void, sum_out: *mut c_void,
rows: i32, hidden_size: i32, eps: f32, stream: *mut c_void);
fn launch_rmsnorm_f32(
x: *const c_void,
gamma: *const c_void,
out: *mut c_void,
rows: i32,
hidden_size: i32,
eps: f32,
stream: *mut c_void,
);
fn launch_rmsnorm_bf16(
x: *const c_void,
gamma: *const c_void,
out: *mut c_void,
rows: i32,
hidden_size: i32,
eps: f32,
stream: *mut c_void,
);
fn launch_add_rmsnorm_bf16(
x: *const c_void,
residual: *const c_void,
gamma: *const c_void,
normed_out: *mut c_void,
sum_out: *mut c_void,
rows: i32,
hidden_size: i32,
eps: f32,
stream: *mut c_void,
);
}
pub fn rmsnorm(x: &Tensor, gamma: &Tensor, eps: f32) -> Tensor {
@@ -20,19 +42,35 @@ pub fn rmsnorm(x: &Tensor, gamma: &Tensor, eps: f32) -> Tensor {
assert_eq!(x.dtype(), gamma.dtype());
let rows = x.numel() / hidden_size;
assert!(rows <= i32::MAX as usize, "too many rows for i32 kernel param");
assert!(hidden_size <= i32::MAX as usize, "hidden_size too large for i32 kernel param");
assert!(
rows <= i32::MAX as usize,
"too many rows for i32 kernel param"
);
assert!(
hidden_size <= i32::MAX as usize,
"hidden_size too large for i32 kernel param"
);
let out = Tensor::empty(x.shape(), x.dtype(), x.device());
unsafe {
match x.dtype() {
DType::F32 => launch_rmsnorm_f32(
x.data_ptr() as _, gamma.data_ptr() as _, out.data_ptr() as *mut c_void,
rows as i32, hidden_size as i32, eps, xserv_cuda::current_stream_raw(),
x.data_ptr() as _,
gamma.data_ptr() as _,
out.data_ptr() as *mut c_void,
rows as i32,
hidden_size as i32,
eps,
xserv_cuda::current_stream_raw(),
),
DType::BF16 => launch_rmsnorm_bf16(
x.data_ptr() as _, gamma.data_ptr() as _, out.data_ptr() as *mut c_void,
rows as i32, hidden_size as i32, eps, xserv_cuda::current_stream_raw(),
x.data_ptr() as _,
gamma.data_ptr() as _,
out.data_ptr() as *mut c_void,
rows as i32,
hidden_size as i32,
eps,
xserv_cuda::current_stream_raw(),
),
_ => panic!("unsupported dtype for rmsnorm"),
}
@@ -56,8 +94,14 @@ pub fn add_rmsnorm(x: &Tensor, residual: &Tensor, gamma: &Tensor, eps: f32) -> (
assert_eq!(gamma.shape(), &[hidden_size]);
let rows = x.numel() / hidden_size;
assert!(rows <= i32::MAX as usize, "too many rows for i32 kernel param");
assert!(hidden_size <= i32::MAX as usize, "hidden_size too large for i32 kernel param");
assert!(
rows <= i32::MAX as usize,
"too many rows for i32 kernel param"
);
assert!(
hidden_size <= i32::MAX as usize,
"hidden_size too large for i32 kernel param"
);
let normed_out = Tensor::empty(x.shape(), DType::BF16, x.device());
let sum_out = Tensor::empty(x.shape(), DType::BF16, x.device());