Gahow Wang
c8e8153702
CUDA kernels (csrc/): - common.cuh: shared warp_reduce_sum/max, block_reduce_sum/max - normalization/rmsnorm.cu: RMSNorm (F32 + BF16) - normalization/layernorm.cu: LayerNorm with Welford (F32 + BF16) - activation/activations.cu: GELU tanh-approx + SiLU (F32 + BF16) - reduce/softmax.cu: safe softmax, 3-pass (F32 + BF16) - embedding/embedding.cu: gather lookup (F32 + BF16) - embedding/rope.cu: RoPE in-place + precomputed cos/sin cache (F32 + BF16) Rust wrappers (xserv-kernels/src/): - rmsnorm.rs, layernorm.rs, activation.rs, softmax.rs, embedding.rs, rope.rs - RopeCache struct with GPU-side precomputation Tests: 12 new tests (ops_test.rs), all passing with good precision: - F32: max_err 1e-6 ~ 1e-9 - BF16: max_err 2e-3 ~ 7e-3 Total: 29 kernel tests + 27 prior = 56 tests passing Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
29 lines
975 B
Rust
29 lines
975 B
Rust
use std::env;
|
|
|
|
fn main() {
|
|
let cuda_path = env::var("CUDA_HOME")
|
|
.or_else(|_| env::var("CUDA_PATH"))
|
|
.unwrap_or_else(|_| "/usr/local/cuda".to_string());
|
|
|
|
println!("cargo:rustc-link-search=native={cuda_path}/lib64");
|
|
println!("cargo:rustc-link-lib=dylib=cudart");
|
|
println!("cargo:rustc-link-lib=dylib=cublas");
|
|
|
|
cc::Build::new()
|
|
.cuda(true)
|
|
.cudart("shared")
|
|
.flag("-gencode=arch=compute_120,code=sm_120")
|
|
.include("../../csrc")
|
|
.file("../../csrc/gemm/naive.cu")
|
|
.file("../../csrc/gemm/tiled.cu")
|
|
.file("../../csrc/normalization/rmsnorm.cu")
|
|
.file("../../csrc/normalization/layernorm.cu")
|
|
.file("../../csrc/activation/activations.cu")
|
|
.file("../../csrc/reduce/softmax.cu")
|
|
.file("../../csrc/embedding/embedding.cu")
|
|
.file("../../csrc/embedding/rope.cu")
|
|
.compile("xserv_kernels");
|
|
|
|
println!("cargo:rerun-if-changed=../../csrc/");
|
|
}
|