Migrate header files to torch stable abi (#44013)

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
   rev: v21.1.2
   hooks:
   - id: clang-format
-    exclude: 'csrc/(moe/topk_softmax_kernels.cu|quantization/gguf/(ggml-common.h|dequantize.cuh|vecdotq.cuh|mmq.cuh|mmvq.cuh))|vllm/third_party/.*'
+    exclude: 'csrc/(moe/topk_softmax_kernels.cu|libtorch_stable/quantization/gguf/(ggml-common.h|dequantize.cuh|vecdotq.cuh|mmq.cuh|mmvq.cuh))|vllm/third_party/.*'
     types_or: [c++, cuda]
     args: [--style=file, --verbose]
 - repo: https://github.com/DavidAnson/markdownlint-cli2

csrc/libtorch_stable/cutlass_extensions/epilogue/scaled_mm_epilogues_c2x.hpp

@@ -2,7 +2,7 @@
 
 #include <torch/csrc/stable/tensor.h>
 
-#include "cutlass_extensions/epilogue/broadcast_load_epilogue_c2x.hpp"
+#include "broadcast_load_epilogue_c2x.hpp"
 
 /*
    This file defines custom epilogues for fusing channel scales, token scales,

csrc/libtorch_stable/fused_qknorm_rope_kernel.cu

@@ -20,7 +20,7 @@
 
 #include "torch_utils.h"
 
-#include "../async_util.cuh"
+#include "async_util.cuh"
 #include "../cuda_compat.h"
 #include "../type_convert.cuh"
 #include "dispatch_utils.h"

csrc/libtorch_stable/quantization/fp4/activation_nvfp4_quant_fusion_kernels.cu

@@ -25,7 +25,7 @@
 #include <cuda_fp8.h>
 
 #include "cuda_utils.h"
-#include "launch_bounds_utils.h"
+#include "libtorch_stable/launch_bounds_utils.h"
 
 // Define before including nvfp4_utils.cuh so the header
 // can use this macro during compilation.

csrc/libtorch_stable/quantization/fp4/mxfp4_experts_quant.cu

@@ -34,7 +34,7 @@
 static_assert(CVT_FP4_ELTS_PER_THREAD == 16,
               "MXFP4 experts quant requires PACK16 mode (CUDA >= 12.9)");
 
-#include "launch_bounds_utils.h"
+#include "libtorch_stable/launch_bounds_utils.h"
 
 namespace vllm {
 

csrc/libtorch_stable/quantization/fp4/nvfp4_experts_quant.cu

@@ -26,7 +26,7 @@
 
 #include "cuda_utils.h"
 #include "nvfp4_utils.cuh"
-#include "launch_bounds_utils.h"
+#include "libtorch_stable/launch_bounds_utils.h"
 
 namespace vllm {
 

csrc/libtorch_stable/quantization/fp4/nvfp4_quant_kernels.cu

@@ -26,7 +26,7 @@
 #include "../../cuda_vec_utils.cuh"
 
 #include "cuda_utils.h"
-#include "launch_bounds_utils.h"
+#include "libtorch_stable/launch_bounds_utils.h"
 
 // Define before including nvfp4_utils.cuh so the header
 // can use this macro during compilation.

csrc/libtorch_stable/quantization/gguf/gguf_kernel.cu

@@ -7,14 +7,11 @@
 
 #include <torch/csrc/stable/ops.h>
 
-// NOTE: These headers are intentionally kept in csrc/quantization/gguf/ (not
-// moved to libtorch_stable) to avoid unnecessary reformatting that would break
-// git rename detection and pollute blame history.
-#include "../../../quantization/gguf/ggml-common.h"
-#include "../../../quantization/gguf/vecdotq.cuh"
-#include "../../../quantization/gguf/dequantize.cuh"
-#include "../../../quantization/gguf/mmvq.cuh"
-#include "../../../quantization/gguf/mmq.cuh"
+#include "ggml-common.h"
+#include "vecdotq.cuh"
+#include "dequantize.cuh"
+#include "mmvq.cuh"
+#include "mmq.cuh"
 #include "moe.cuh"
 #include "moe_vec.cuh"
 

csrc/libtorch_stable/topk.cu

@@ -7,7 +7,7 @@
 #include "torch_utils.h"
 
 #ifndef USE_ROCM
-  #include "../persistent_topk.cuh"
+  #include "persistent_topk.cuh"
 #endif
 
 namespace {