[Bugfix] Guard mxfp4_experts_quant bindings on ENABLE_NVFP4_SM100 (#40191)

Signed-off-by: ultranationalism <www913363043@gmail.com>
Signed-off-by: mgoin <mike.goin12@gmail.com>
Co-authored-by: mgoin <mike.goin12@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
mysterious hhhh
2026-04-18 13:58:46 -07:00
committed by GitHub
co-authored by mgoin Claude Opus 4.7
parent ed0622e3a8
commit d0359f3e04
3 changed files with 12 additions and 20 deletions
+2 -6
View File
@@ -252,12 +252,8 @@ STABLE_TORCH_LIBRARY_IMPL(_C, CUDA, ops) {
ops.impl("silu_and_mul_scaled_fp4_experts_quant",
TORCH_BOX(&silu_and_mul_scaled_fp4_experts_quant));
ops.impl("silu_and_mul_nvfp4_quant", TORCH_BOX(&silu_and_mul_nvfp4_quant));
ops.impl("mxfp4_experts_quant", TORCH_BOX(&mxfp4_experts_quant));
ops.impl("silu_and_mul_mxfp4_experts_quant",
TORCH_BOX(&silu_and_mul_mxfp4_experts_quant));
// W4A8 ops: impl registrations are in the source files
// (w4a8_mm_entry.cu and w4a8_grouped_mm_entry.cu)
// mxfp4_experts_quant: registered in mxfp4_experts_quant.cu (SM100 only).
// W4A8 ops: registered in w4a8_mm_entry.cu / w4a8_grouped_mm_entry.cu.
#endif
}