Gahow Wang
76487b7963
Replace the W8A16 dequant→BF16-GEMM path with native FP8×FP8→BF16 GEMM using cuBLASLt on Blackwell (RTX 5090). Both weights (static FP8 E4M3) and activations (dynamically quantized per-row) are processed directly on FP8 tensor cores. Key implementation details: - cuBLASLt on Blackwell requires transA=T for FP8, so expert weights are transposed during model loading ([E,K,N] → [E,N,K]) - Per-row activation quantization kernel (absmax/448 → FP8 E4M3) - Post-GEMM row-wise rescaling recovers per-token precision - Per-expert loop (not batched) due to cuBLASLt FP8 scale constraints The same FP8 quantized model files work — no re-quantization needed. Activation quantization happens dynamically at inference time. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
40 lines
1.5 KiB
Rust
40 lines
1.5 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");
|
|
println!("cargo:rustc-link-lib=dylib=cublasLt");
|
|
|
|
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")
|
|
.file("../../csrc/moe/moe_kernels.cu")
|
|
.file("../../csrc/quantization/dequant_fp8.cu")
|
|
.file("../../csrc/quantization/quantize_fp8.cu")
|
|
.compile("xserv_kernels");
|
|
|
|
println!("cargo:rerun-if-changed=../../csrc/");
|
|
}
|