Merge pull request 'finish DequantizeInt8 #87' (#651) from ZZZJ/GPUCodeForces:DequantizeInt8 into main

S1/ZZZJ_#87/dequantize_int8_cuda.py

@@ -0,0 +1,80 @@
+import torch
+import torch.nn as nn
+from torch.utils.cpp_extension import load_inline
+
+dequant_source = """
+#include <torch/extension.h>
+#include <cuda_runtime.h>
+
+__global__ void dequantize_kernel(const int8_t* __restrict__ input, 
+                                  float* __restrict__ output, 
+                                  float scale, 
+                                  int num_elements) {
+
+    int idx = blockIdx.x * blockDim.x + threadIdx.x;
+    int stride = blockDim.x * gridDim.x;
+
+    const char4* vec_input = reinterpret_cast<const char4*>(input);
+    float4* vec_output = reinterpret_cast<float4*>(output);
+    
+    int vec_elements = num_elements / 4;
+
+    for (int i = idx; i < vec_elements; i += stride) {
+        char4 loaded = vec_input[i];
+        
+        float4 res;
+        res.x = (float)loaded.x * scale;
+        res.y = (float)loaded.y * scale;
+        res.z = (float)loaded.z * scale;
+        res.w = (float)loaded.w * scale;
+        
+        vec_output[i] = res;
+    }
+
+    int tail_start = vec_elements * 4;
+    for (int i = tail_start + idx; i < num_elements; i += stride) {
+        output[i] = (float)input[i] * scale;
+    }
+}
+
+torch::Tensor dequantize_cuda(torch::Tensor input, float scale) {
+
+    auto output = torch::empty_like(input, input.options().dtype(torch::kFloat32));
+    
+    int num_elements = input.numel();
+    
+    const int block_size = 256;
+
+    int vec_size = (num_elements + 3) / 4;
+    int grid_size = (vec_size + block_size - 1) / block_size;
+    
+    if (grid_size > 65535) grid_size = 65535;
+
+    dequantize_kernel<<<grid_size, block_size>>>(
+        (int8_t*)input.data_ptr<int8_t>(),
+        output.data_ptr<float>(),
+        scale,
+        num_elements
+    );
+    
+    return output;
+}
+"""
+
+dequant_cpp_source = "torch::Tensor dequantize_cuda(torch::Tensor input, float scale);"
+
+module = load_inline(
+    name="dequant_impl",
+    cpp_sources=dequant_cpp_source,
+    cuda_sources=dequant_source,
+    functions=["dequantize_cuda"],
+    verbose=True
+)
+
+class ModelNew(torch.nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.module = module
+
+    def forward(self, x_int8, scale):
+        return self.module.dequantize_cuda(x_int8, scale.item())

S1/ZZZJ_#87/dequantize_int8_torch.py

@@ -0,0 +1,23 @@
+import torch
+import torch.nn as nn
+
+class Model(nn.Module):
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x_int8, scale):
+
+        return x_int8.to(torch.float32) * scale
+
+
+shape = (16, 4096, 4096)
+
+def get_inputs():
+
+    x_int8 = torch.randint(-128, 127, shape, dtype=torch.int8).cuda()
+
+    scale = torch.tensor(0.005, dtype=torch.float32).cuda()
+    return [x_int8, scale]
+
+def get_init_inputs():
+    return []

S1/ZZZJ_#87/prompt.txt

@@ -0,0 +1,31 @@
+You write custom CUDA kernels to replace the pytorch operators in the given architecture to get speedups.   
+  
+You have complete freedom to choose the set of operators you want to replace. You may make the decision to replace some operators with custom CUDA kernels and leave others unchanged. You may replace multiple operators with custom implementations, consider operator fusion opportunities (combining multiple operators into a single kernel, for example, combining matmul+relu), or algorithmic changes (such as online softmax). You are only limited by your imagination.  
+  
+Here's an example to show you the syntax of inline embedding custom CUDA operators in torch: The example given architecture is:   
+  
+python
+import torch
+import torch.nn as nn
+
+class Model(nn.Module):
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x_int8, scale):
+
+        return x_int8.to(torch.float32) * scale
+
+
+shape = (16, 4096, 4096)
+
+def get_inputs():
+
+    x_int8 = torch.randint(-128, 127, shape, dtype=torch.int8).cuda()
+
+    scale = torch.tensor(0.005, dtype=torch.float32).cuda()
+    return [x_int8, scale]
+
+def get_init_inputs():
+    return []
+```

S1/ZZZJ_#87/run_code.py

@@ -0,0 +1,74 @@
+###########################################################
+# 性能和精度验证程序
+###########################################################
+import torch
+import torch.nn as nn
+import time
+from dequantize_int8_torch import Model,get_inputs,get_init_inputs
+from dequantize_int8_cuda import ModelNew
+
+def run_benchmark():
+    # 检查 CUDA 是否可用
+    if not torch.cuda.is_available():
+        print("CUDA 不可用，请确保您有可用的 NVIDIA GPU 并已正确安装 PyTorch CUDA 版本。")
+        return
+    else:
+        device = torch.device("cuda")
+
+    # 初始化模型
+    init_inputs = get_init_inputs()
+    init_inputs = [
+        x.cuda(device=device) if isinstance(x, torch.Tensor) else x for x in init_inputs
+    ]
+    inputs = get_inputs()
+    inputs = [
+        x.cuda(device=device) if isinstance(x, torch.Tensor) else x for x in inputs
+    ]
+
+    torch_model = Model(*init_inputs).cuda()
+    cuda_model = ModelNew(*init_inputs).cuda()
+
+    torch_model.eval()
+    cuda_model.eval()
+
+    print("-------------------- 精度对齐验证 --------------------")
+    with torch.no_grad():
+        output_torch = torch_model( *inputs)
+        output_cuda = cuda_model(*inputs)
+
+    precision_flag = torch.allclose(output_torch, output_cuda,rtol=1e-03)
+    if precision_flag:
+        print("✅ 精度对齐：两个模型的输出结果非常接近。")
+    else:
+        print("❌ 精度不一致！")
+        
+    print("\n-------------------- 性能加速比测试 --------------------")
+    num_iterations = 100 
+    
+    # PyTorch 模型计时
+    torch.cuda.synchronize()
+    start_time = time.time()
+    for _ in range(num_iterations):
+        _ = torch_model(*inputs)
+    torch.cuda.synchronize()
+    torch_time = (time.time() - start_time) / num_iterations
+    
+    # 自定义 CUDA 内核计时
+    torch.cuda.synchronize()
+    start_time = time.time()
+    for _ in range(num_iterations):
+        _ = cuda_model(*inputs)
+    torch.cuda.synchronize()
+    cuda_time = (time.time() - start_time) / num_iterations
+    
+    print(f"PyTorch torch.relu 平均执行时间: {torch_time:.6f} 秒")
+    print(f"自定义 CUDA 内核 平均执行时间: {cuda_time:.6f} 秒")
+    speedup = 0
+    if cuda_time > 0:
+        speedup = torch_time / cuda_time
+        print(f"加速比 (Speedup): {speedup:.2f}x")
+    else:
+        print("CUDA 内核执行时间为0，无法计算加速比。")
+    return precision_flag,speedup
+if __name__ == "__main__":
+    precision_flag,speedup = run_benchmark()