finish InverseReinforcementLearningLoss #92

S1/uucoco_#92/InverseReinforcementLearningLoss_cuda.py

@@ -0,0 +1,46 @@
+import torch
+import torch.nn as nn
+from torch.utils.cpp_extension import load_inline
+
+cuda_source = """
+#include <torch/extension.h>
+#include <cuda_runtime.h>
+
+__global__ void irl_kernel(const float* pred_rewards, const float* expert_log_probs, const float* policy_log_probs, float* expert_out, float* policy_out, int size) {
+    int idx = blockIdx.x * blockDim.x + threadIdx.x;
+    if (idx < size) {
+        expert_out[idx] = -pred_rewards[idx] * expert_log_probs[idx];
+        policy_out[idx] = pred_rewards[idx] * policy_log_probs[idx];
+    }
+}
+
+torch::Tensor irl_cuda(torch::Tensor pred_rewards, torch::Tensor expert_log_probs, torch::Tensor policy_log_probs) {
+    auto size = pred_rewards.numel();
+    auto expert_out = torch::empty_like(pred_rewards);
+    auto policy_out = torch::empty_like(pred_rewards);
+    const int block_size = 256;
+    int num_blocks = (size + block_size - 1) / block_size;
+    irl_kernel<<<num_blocks, block_size>>>(pred_rewards.data_ptr<float>(), expert_log_probs.data_ptr<float>(), policy_log_probs.data_ptr<float>(), expert_out.data_ptr<float>(), policy_out.data_ptr<float>(), size);
+    return expert_out.mean() + policy_out.mean();
+}
+"""
+
+cpp_source = """
+torch::Tensor irl_cuda(torch::Tensor pred_rewards, torch::Tensor expert_log_probs, torch::Tensor policy_log_probs);
+"""
+
+irl_module = load_inline(
+    name="inverse_rl",
+    cpp_sources=cpp_source,
+    cuda_sources=cuda_source,
+    functions=["irl_cuda"],
+    verbose=True
+)
+
+class ModelNew(torch.nn.Module):
+    def __init__(self):
+        super(ModelNew, self).__init__()
+        self.irl_module = irl_module
+
+    def forward(self, pred_rewards, expert_log_probs, policy_log_probs):
+        return self.irl_module.irl_cuda(pred_rewards, expert_log_probs, policy_log_probs)

S1/uucoco_#92/InverseReinforcementLearningLoss_torch.py

@@ -0,0 +1,28 @@
+import torch
+import torch.nn as nn
+
+
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+
+    def forward(self, pred_rewards: torch.Tensor, expert_log_probs: torch.Tensor,
+                policy_log_probs: torch.Tensor) -> torch.Tensor:
+        expert_loss = -(pred_rewards * expert_log_probs).mean()
+        policy_loss = (pred_rewards * policy_log_probs).mean()
+        loss = expert_loss + policy_loss
+        return loss
+
+
+batch_size = 32
+
+
+def get_inputs():
+    pred_rewards = torch.randn(batch_size)
+    expert_log_probs = torch.randn(batch_size)
+    policy_log_probs = torch.randn(batch_size)
+    return [pred_rewards, expert_log_probs, policy_log_probs]
+
+
+def get_init_inputs():
+    return []

S1/uucoco_#92/prompt.txt

@@ -0,0 +1,53 @@
+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 chunk+gelu+elementwise_mul), or algorithmic changes (such as optimized memory access patterns). You are only limited by your imagination.
+PyTorch C++/CUDA Extension: Inline compilation via torch.utils.cpp_extension.load_inline.
+
+Simple Element-wise CUDA Kernel: Parallel computation per element using blockIdx.x * blockDim.x + threadIdx.x.
+
+Single‑Kernel Dual Output: Computes two terms in one kernel:
+
+expert_out[i] = -pred_rewards[i] * expert_log_probs[i]
+
+policy_out[i] = pred_rewards[i] * policy_log_probs[i]
+
+Fixed Block Size: Uses 256 threads per block.
+
+Automatic Mean Reduction: Returns expert_out.mean() + policy_out.mean() directly in CUDA wrapper.
+
+Lazy Module Loading: CUDA extension compiled once and stored as a class attribute.
+
+Minimal Python Wrapper: Forward pass directly calls the compiled CUDA function.
+
+
+
+
+
+
+Here's an example to show you the syntax of inline embedding custom CUDA operators in torch: The example given architecture is:
+import torch
+import torch.nn as nn
+
+
+class Model(nn.Module):
+    def __init__(self):
+        super(Model, self).__init__()
+
+    def forward(self, pred_rewards: torch.Tensor, expert_log_probs: torch.Tensor,
+                policy_log_probs: torch.Tensor) -> torch.Tensor:
+        expert_loss = -(pred_rewards * expert_log_probs).mean()
+        policy_loss = (pred_rewards * policy_log_probs).mean()
+        loss = expert_loss + policy_loss
+        return loss
+
+
+batch_size = 32
+
+
+def get_inputs():
+    pred_rewards = torch.randn(batch_size)
+    expert_log_probs = torch.randn(batch_size)
+    policy_log_probs = torch.randn(batch_size)
+    return [pred_rewards, expert_log_probs, policy_log_probs]
+
+
+def get_init_inputs():
+    return []

S1/uucoco_#92/run_code.py

@@ -0,0 +1,77 @@
+###########################################################
+# 性能和精度验证程序
+###########################################################
+import torch
+import torch.nn as nn
+import time
+from InverseReinforcementLearningLoss_torch import Model, get_inputs, get_init_inputs
+from InverseReinforcementLearningLoss_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()