Tiny fix sampler error when prob is not contiguous

[fzyzcjy]

Motivation

[2025-05-27 01:00:47 DP7 TP15] TpModelWorkerClient hit an exception: Traceback (most recent call last):
  File "/host_home/primary_synced/sglang/python/sglang/srt/managers/tp_worker_overlap_thread.py", line 118, in forward_thread_func
    self.forward_thread_func_()
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/host_home/primary_synced/sglang/python/sglang/srt/managers/tp_worker_overlap_thread.py", line 151, in forward_thread_func_
    self.worker.forward_batch_generation(
  File "/host_home/primary_synced/sglang/python/sglang/srt/managers/tp_worker.py", line 211, in forward_batch_generation
    next_token_ids = self.model_runner.sample(
  File "/host_home/primary_synced/sglang/python/sglang/srt/model_executor/model_runner.py", line 1264, in sample
    next_token_ids = self.sampler(
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/nn/modules/module.py", line 1750, in _call_impl
    return forward_call(*args, **kwargs)
  File "/host_home/primary_synced/sglang/python/sglang/srt/layers/sampler.py", line 103, in forward
    batch_next_token_ids = top_k_top_p_sampling_from_probs(
  File "/usr/local/lib/python3.10/dist-packages/sgl_kernel/sampling.py", line 293, in top_k_top_p_sampling_from_probs
    return _top_k_top_p_sampling_from_probs_internal(
  File "/usr/local/lib/python3.10/dist-packages/sgl_kernel/sampling.py", line 205, in _top_k_top_p_sampling_from_probs_internal
    torch.ops.sgl_kernel.top_k_top_p_sampling_from_probs.default(
  File "/usr/local/lib/python3.10/dist-packages/torch/_ops.py", line 723, in __call__
    return self._op(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/utils/_device.py", line 104, in __torch_function__
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/torch/_ops.py", line 723, in __call__
    return self._op(*args, **kwargs)
RuntimeError: probs must be contiguous

Modifications

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.