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

phase 15: Tensor::empty + CUDA Graph infra — 50.3 tok/s (140% of HF, 45% roofline)

Browse Source 
Two optimizations:

1. Tensor::empty() — skip cudaMemset for output tensors
   All kernel wrappers that fully overwrite their output now use
   Tensor::empty() instead of Tensor::zeros(). Eliminates ~756
   cudaMemset calls per decode step (21 per layer × 36 layers).
   Improvement: 46.6 → 50.3 tok/s (+8%).

2. CUDA Graph infrastructure (for future use)
   Added FFI bindings (cudaStreamBeginCapture, cudaGraphInstantiate,
   cudaGraphLaunch) and RAII CudaGraph wrapper. Not yet used in the
   forward pass due to variable kv_len, but provides foundation for
   future graph-based decode optimization.

Ablation (dash5, RTX 5090, Qwen3-8B BF16, serial decode):

| Optimization | tok/s | vs HF | Roofline |
|-------------|-------|-------|----------|
| Phase 14 baseline | 12.9 | 36% | 12% |
| + Fused kernels | 13.2 | 37% | 12% |
| + Batched decode | 13.2 (serial) | 37% | 12% |
| + Custom GEMV | 46.6 | 130% | 42% |
| + Tensor::empty | 50.3 | 140% | 45% |

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-05-22 23:57:34 +08:00
parent e207523e21
commit d5532ef209
13 changed files with 170 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
crates/xserv-kernels/src/activation.rs
View File

@@ -18,7 +18,7 @@ unsafe extern "C" {
fn dispatch_unary(x: &Tensor, f32_fn: unsafe extern "C" fn(*const c_void, *mut c_void, i32, *mut c_void),
bf16_fn: unsafe extern "C" fn(*const c_void, *mut c_void, i32, *mut c_void)) -> Tensor {
assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
let out = Tensor::zeros(x.shape(), x.dtype(), x.device());
let out = Tensor::empty(x.shape(), x.dtype(), x.device());
let n = x.numel() as i32;
unsafe {
match x.dtype() {
@@ -37,7 +37,7 @@ fn dispatch_binary(a: &Tensor, b: &Tensor,
assert!(a.is_contiguous() && b.is_contiguous());
assert!(matches!(a.device(), Device::Cuda(_)));
assert_eq!(a.dtype(), b.dtype());
let out = Tensor::zeros(a.shape(), a.dtype(), a.device());
let out = Tensor::empty(a.shape(), a.dtype(), a.device());
let n = a.numel() as i32;
unsafe {
match a.dtype() {
@@ -54,7 +54,7 @@ pub fn silu(x: &Tensor) -> Tensor { dispatch_unary(x, launch_silu_f32, launch_si
pub fn scale(x: &Tensor, scale_val: f32) -> Tensor {
assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
let out = Tensor::zeros(x.shape(), x.dtype(), x.device());
let out = Tensor::empty(x.shape(), x.dtype(), x.device());
let n = x.numel() as i32;
unsafe {
match x.dtype() {
@@ -76,7 +76,7 @@ pub fn silu_mul(gate: &Tensor, up: &Tensor) -> Tensor {
assert!(gate.is_contiguous() && up.is_contiguous());
assert!(matches!(gate.device(), Device::Cuda(_)));
assert_eq!(gate.dtype(), DType::BF16, "silu_mul requires BF16");
let out = Tensor::zeros(gate.shape(), gate.dtype(), gate.device());
let out = Tensor::empty(gate.shape(), gate.dtype(), gate.device());
let n = gate.numel() as i32;
unsafe {
launch_silu_mul_bf16(