[9/n] Migrate attention and cache kernels to torch stable ABI (continued) (#43717)

Signed-off-by: Chris Leonard <chleonar@redhat.com>
Signed-off-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Co-authored-by: Mikayla Gawarecki <mikaylagawarecki@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
This commit is contained in:
Chris Leonard
2026-05-29 04:44:45 +00:00
committed by GitHub
co-authored by Mikayla Gawarecki Shengqi Chen
parent 710f077617
commit 22a58640b4
23 changed files with 909 additions and 720 deletions
@@ -17,7 +17,7 @@
#include <torch/csrc/stable/tensor.h>
#include "libtorch_stable/torch_utils.h"
#include "libtorch_stable/dispatch_utils.h"
#include "cuda_vec_utils.cuh"
#include "../../cuda_vec_utils.cuh"
#include <cuda_runtime_api.h>
#include <cuda_runtime.h>
@@ -27,7 +27,7 @@
#include <torch/csrc/stable/tensor.h>
#include "libtorch_stable/torch_utils.h"
#include "libtorch_stable/dispatch_utils.h"
#include "cuda_vec_utils.cuh"
#include "../../cuda_vec_utils.cuh"
#include "cuda_utils.h"
#include "nvfp4_utils.cuh"
@@ -17,7 +17,7 @@
#include <torch/csrc/stable/tensor.h>
#include "libtorch_stable/torch_utils.h"
#include "libtorch_stable/dispatch_utils.h"
#include "cuda_vec_utils.cuh"
#include "../../cuda_vec_utils.cuh"
#include <cuda_runtime_api.h>
#include <cuda_runtime.h>
@@ -23,7 +23,7 @@
#include "libtorch_stable/torch_utils.h"
#include "libtorch_stable/dispatch_utils.h"
#include "cuda_vec_utils.cuh"
#include "../../cuda_vec_utils.cuh"
#include "cuda_utils.h"
#include "launch_bounds_utils.h"
@@ -20,7 +20,7 @@
#include <cuda_fp8.h>
#include <utility>
#include "cuda_vec_utils.cuh"
#include "../../cuda_vec_utils.cuh"
#if defined(NVFP4_ENABLE_ELTS16) && defined(CUDA_VERSION) && \
CUDA_VERSION >= 12090