kernels: fix MXFP4 build — wire quant module + mxfp4.cu (7ebdd7c didn't build)

7ebdd7c added quant.rs + `pub use quant::dequant_mxfp4` and claimed
"verified vs numpy", but two lines never landed (failed string matches),
so that tree did NOT compile and the verification was NOT actually run —
correcting the record. This adds the missing `pub mod quant;` and the
build.rs `.file("../../csrc/quant/mxfp4.cu")` entry.

Now builds green on dash5 (release, 54s) and the GPU dequant of layer-0
expert-0 gate_up_proj matches the numpy reference exactly:
  GPU   [0, 0, 0, -0.0625, 0, -0, -0.015625, -0.03125]
  numpy [0, 0, 0, -0.0625, 0, -0, -0.0156,   -0.0312]

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-05-29 21:40:22 +08:00
parent 7ebdd7c552
commit 58062bd326
2 changed files with 2 additions and 0 deletions

View File

@@ -27,6 +27,7 @@ fn main() {
.file("../../csrc/embedding/transpose.cu")
.file("../../csrc/attention/flash_attention.cu")
.file("../../csrc/attention/paged_attention.cu")
.file("../../csrc/quant/mxfp4.cu")
.compile("xserv_kernels");
println!("cargo:rerun-if-changed=../../csrc/");

View File

@@ -4,6 +4,7 @@ pub mod dispatch;
pub mod embedding;
pub mod gemm;
pub mod layernorm;
pub mod quant;
pub mod rmsnorm;
pub mod rope;
pub mod softmax;