Files
wehub-resource-sync 94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

130 lines
3.0 KiB
C++

#pragma once
#if USE_ROCM
#include <hip/hip_common.h>
// Adapted from flashinfer-rocm [PR#491](https://github.com/flashinfer-ai/flashinfer/pull/491)
namespace sgl_hip {
template <>
struct vec_t<float, 1> {
float data;
SGL_HIP_INLINE float& operator[](size_t i) {
return ((float*)(&data))[i];
}
SGL_HIP_INLINE const float& operator[](size_t i) const {
return ((const float*)(&data))[i];
}
SGL_HIP_INLINE float* ptr() {
return reinterpret_cast<float*>(&data);
}
SGL_HIP_INLINE void load(const float* ptr);
SGL_HIP_INLINE void store(float* ptr) const;
template <typename T>
SGL_HIP_INLINE void cast_from(const vec_t<T, 1>& src) {
cast_from_impl(*this, src);
}
template <typename T>
SGL_HIP_INLINE void cast_load(const T* ptr) {
cast_load_impl(*this, ptr);
}
template <typename T>
SGL_HIP_INLINE void cast_store(T* ptr) const {
cast_store_impl(ptr, *this);
}
};
SGL_HIP_INLINE void vec_t<float, 1>::load(const float* ptr) {
data = *ptr;
}
SGL_HIP_INLINE void vec_t<float, 1>::store(float* ptr) const {
*ptr = data;
}
// float x 2
template <>
struct vec_t<float, 2> {
float2 data;
SGL_HIP_INLINE float& operator[](size_t i) {
return ((float*)(&data))[i];
}
SGL_HIP_INLINE const float& operator[](size_t i) const {
return ((const float*)(&data))[i];
}
SGL_HIP_INLINE float* ptr() {
return reinterpret_cast<float*>(&data);
}
SGL_HIP_INLINE void load(const float* ptr);
SGL_HIP_INLINE void store(float* ptr) const;
template <typename T>
SGL_HIP_INLINE void cast_from(const vec_t<T, 2>& src) {
cast_from_impl(*this, src);
}
template <typename T>
SGL_HIP_INLINE void cast_load(const T* ptr) {
cast_load_impl(*this, ptr);
}
template <typename T>
SGL_HIP_INLINE void cast_store(T* ptr) const {
cast_store_impl(ptr, *this);
}
};
SGL_HIP_INLINE void vec_t<float, 2>::load(const float* ptr) {
data = *((float2*)ptr);
}
SGL_HIP_INLINE void vec_t<float, 2>::store(float* ptr) const {
*((float2*)ptr) = data;
}
// float x 4 or more
template <size_t vec_size>
struct vec_t<float, vec_size> {
float4 data[vec_size / 4];
SGL_HIP_INLINE float& operator[](size_t i) {
return ((float*)(data))[i];
}
SGL_HIP_INLINE const float& operator[](size_t i) const {
return ((const float*)(data))[i];
}
SGL_HIP_INLINE float* ptr() {
return reinterpret_cast<float*>(&data);
}
SGL_HIP_INLINE void load(const float* ptr) {
#pragma unroll
for (size_t i = 0; i < vec_size / 4; ++i) {
data[i] = ((float4*)ptr)[i];
}
}
SGL_HIP_INLINE void store(float* ptr) const {
#pragma unroll
for (size_t i = 0; i < vec_size / 4; ++i) {
((float4*)ptr)[i] = data[i];
}
}
template <typename T>
SGL_HIP_INLINE void cast_from(const vec_t<T, vec_size>& src) {
cast_from_impl(*this, src);
}
template <typename T>
SGL_HIP_INLINE void cast_load(const T* ptr) {
cast_load_impl(*this, ptr);
}
template <typename T>
SGL_HIP_INLINE void cast_store(T* ptr) const {
cast_store_impl(ptr, *this);
}
};
} // namespace sgl_hip
#endif