fix: add disable flashinfer e2e benchmark

[zhyncs]

Thank you for your contribution, we really appreciate it. The following instructions will help improve your pull request and make it easier to receive feedback. If there are any items you don't understand, don't worry. Just submit the pull request and ask the maintainers for help.

Motivation

Please explain the motivation behind this PR and the goal you aim to achieve with it.

Modification

Briefly describe the changes made in this PR.

Checklist

1. Ensure pre-commit pre-commit run --all-files or other linting tools are used to fix potential lint issues.
2. Confirm that modifications are covered by complete unit tests. If not, please add more unit tests for correctness.
3. Modify documentation as needed, such as docstrings or example tutorials.

[zhyncs]

This is a naive CI verification to discover potential illegal memory issues when disable FlashInfer is enabled. ref #981

Traceback (most recent call last):
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/tp_worker.py", line 223, in exposed_step
    self.forward_step()
  File "/data/zhyncs/runner-v2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/tp_worker.py", line 252, in forward_step
    self.forward_decode_batch(self.running_batch)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/tp_worker.py", line 608, in forward_decode_batch
    next_token_ids = batch.sample(output.next_token_logits)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/schedule_batch.py", line 766, in sample
    if not torch.all(success):
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.


Exception in ControllerSingle:
Traceback (most recent call last):
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/controller_single.py", line 166, in start_controller_process
    controller.loop_for_forward()
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/controller_single.py", line 103, in loop_for_forward
    out_pyobjs = self.tp_server.exposed_step(recv_reqs)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/tp_worker.py", line 223, in exposed_step
    self.forward_step()
  File "/data/zhyncs/runner-v2/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/tp_worker.py", line 252, in forward_step
    self.forward_decode_batch(self.running_batch)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/tp_worker.py", line 608, in forward_decode_batch
    next_token_ids = batch.sample(output.next_token_logits)
  File "/data/zhyncs/runner-v2/actions-runner/_work/sglang/sglang/python/sglang/srt/managers/schedule_batch.py", line 766, in sample
    if not torch.all(success):
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

[merrymercy]

move to #1039