[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:
co-authored by
mgoin
Claude Opus 4.7
parent
ed0622e3a8
commit
d0359f3e04
@@ -23,6 +23,7 @@
|
||||
#include <cuda_runtime.h>
|
||||
#include <cuda_fp8.h>
|
||||
|
||||
#include <torch/csrc/stable/library.h>
|
||||
#include <torch/csrc/stable/tensor.h>
|
||||
#include "libtorch_stable/torch_utils.h"
|
||||
#include "libtorch_stable/dispatch_utils.h"
|
||||
@@ -420,3 +421,12 @@ void silu_and_mul_mxfp4_experts_quant(
|
||||
stream);
|
||||
});
|
||||
}
|
||||
|
||||
// Registered here (not torch_bindings.cpp) because VLLM_GPU_FLAGS is applied
|
||||
// only under COMPILE_LANGUAGE:CUDA, so ENABLE_NVFP4_SM100 is invisible to
|
||||
// .cpp files and cannot gate the registration from there.
|
||||
STABLE_TORCH_LIBRARY_IMPL(_C, CUDA, m) {
|
||||
m.impl("mxfp4_experts_quant", TORCH_BOX(&mxfp4_experts_quant));
|
||||
m.impl("silu_and_mul_mxfp4_experts_quant",
|
||||
TORCH_BOX(&silu_and_mul_mxfp4_experts_quant));
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user