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

7
crates/xserv-kernels/src/gemm.rs
View File

@@ -98,7 +98,9 @@ pub fn matmul(a: &Tensor, b: &Tensor, backend: GemmBackend) -> Tensor {
let n = b.shape()[1];
let dtype = a.dtype();
let c = Tensor::zeros(&[m, n], dtype, a.device());
// All backends (naive, tiled, cuBLAS with beta=0, custom GEMV) fully
// overwrite every element of C, so we skip the cudaMemset.
let c = Tensor::empty(&[m, n], dtype, a.device());
let a_ptr = a.data_ptr() as *const c_void;
let b_ptr = b.data_ptr() as *const c_void;
@@ -202,7 +204,8 @@ pub fn batched_matmul(a: &Tensor, b: &Tensor) -> Tensor {
let mut out_shape: Vec<usize> = a.shape()[..ndim - 2].to_vec();
out_shape.push(m);
out_shape.push(n);
let c = Tensor::zeros(&out_shape, a.dtype(), a.device());
// cuBLAS with beta=0 fully overwrites every element of C.
let c = Tensor::empty(&out_shape, a.dtype(), a.device());
let dtype = a.dtype();
let (a_type, b_type, c_type) = match dtype {