[webgpu] fix runtime error caused by buffer release too early

[fs-eire]

Description

Fix runtime error caused by buffer release too early

Motivation and Context

#25276 introduces buffer usage optimization, which reduced the peak GPU memory usage. However, the implementation may cause issue in some situations because the buffer is released too early. This PR fixes the issue.

[Copilot]

Pull Request Overview

This PR fixes a runtime error in the WebGPU buffer manager where buffers were being released prematurely, following optimizations introduced in #25276. The fix implements a deferred buffer release mechanism to prevent buffers from being freed while still in use.

Key changes:

• Buffers that can't be cached are now stored in a pending list instead of being immediately released
• Buffer release is deferred until the OnRefresh method is called, ensuring buffers remain valid during execution
• Added a new member variable to track pending buffers awaiting release

Comments suppressed due to low confidence (1)

onnxruntime/core/providers/webgpu/buffer_manager.cc:247

• The member variable 'pending_buffers' should follow the existing naming convention with a trailing underscore to match other private members like 'buckets_' and 'buckets_limit_'.

  std::vector<std::pair<WGPUBuffer, size_t>> pending_buffers;

[qjia7]

@fs-eire Can you point out the runtime errors how to reproduce them? Maybe @feich-ms can take a further look to follow up. A test case will also be good.

[qjia7]

Sorry that I though it was a revert. Now I understand the changes. LGTM. Thanks.