Gahow Wang
2be27d6d94
New CUDA kernels (csrc/embedding/transpose.cu): - reshape_heads_bf16: [S, H*D] → [1, H, S, D] - merge_heads_bf16: [1, H, S, D] → [S, H*D] - transpose_hsd_to_shd_bf16: [1, H, S, D] → [S, H, D] (for RoPE) - transpose_shd_to_hsd_bf16: [S, H, D] → [1, H, S, D] (from RoPE) - repeat_kv_bf16: [1, KV_H, S, D] → [1, KV_H*n_rep, S, D] Rust wrappers (xserv-kernels/src/transpose.rs): - reshape_heads_gpu, merge_heads_gpu, transpose_for/from_rope_gpu, repeat_kv_gpu Qwen3 forward_gpu_cache now uses all GPU kernels — zero CPU data round-trips. Result: 50/50 self-consistent, 3-5% faster (TBT 142→137ms) Remaining bottleneck: ~900 device::synchronize() calls + 252 cuBLAS handle creations per token (Phase 15 targets) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
31 lines
1.1 KiB
Rust
31 lines
1.1 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/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")
|
|
.file("../../csrc/attention/causal_mask.cu")
|
|
.file("../../csrc/embedding/transpose.cu")
|
|
.compile("xserv_kernels");
|
|
|
|
println!("cargo:rerun-if-changed=../../csrc/");
|
|
}
|