13ae3de69e
Three new CUDA kernels and one rewrite: - reshape_and_cache: scatter K/V into paged pool in a single kernel per layer, replacing the Rust-side per-token per-head cudaMemcpy loop. Includes both single-sequence (prefill) and batched (decode) variants. - argmax: GPU-side BF16 argmax with warp-shuffle reduction. Greedy decode now only D2H-transfers B×4 bytes (token ids) instead of the full [B, vocab] logits tensor. - GEMV rewrite: fused zero-init inside the K-split kernel eliminates the cudaMemsetAsync call, reducing launches from 3 to 2 per GEMV. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
36 lines
1.3 KiB
Rust
36 lines
1.3 KiB
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/gemm/gemv.cu")
|
|
.file("../../csrc/normalization/rmsnorm.cu")
|
|
.file("../../csrc/normalization/layernorm.cu")
|
|
.file("../../csrc/activation/activations.cu")
|
|
.file("../../csrc/reduce/softmax.cu")
|
|
.file("../../csrc/reduce/argmax.cu")
|
|
.file("../../csrc/embedding/embedding.cu")
|
|
.file("../../csrc/embedding/rope.cu")
|
|
.file("../../csrc/attention/causal_mask.cu")
|
|
.file("../../csrc/embedding/transpose.cu")
|
|
.file("../../csrc/attention/flash_attention.cu")
|
|
.file("../../csrc/attention/paged_attention.cu")
|
|
.file("../../csrc/attention/reshape_and_cache.cu")
|
|
.compile("xserv_kernels");
|
|
|
|
println!("cargo:rerun-if-changed=../../csrc/");
|
|
}
|