Do not initialize scratch space when there are no ExLlamaV2 layers (#2015)

# What does this PR do?

Do not attempt to allocate ExLlamaV2 scratch buffers when there are no
ExLlama2 layers. Avoids a crash in warmup for models that cannot use
exllama when ExLlamaV2 is installed.

## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
      Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
      to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation).
- [ ] Did you write any new necessary tests?


## Who can review?

Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.

<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @


@OlivierDehaene OR @Narsil

 -->

server/text_generation_server/layers/gptq/exllamav2.py

@@ -145,6 +145,11 @@ def set_device(device):
 def create_exllama_buffers(max_total_tokens: int):
     global LAYERS, DEVICE
 
+    # No need to initialize scratch space if there are no layers
+    # that use ExLLamav2.
+    if len(LAYERS) == 0:
+        return
+
     # Find the size of the scratch space.
     scratch_bytes = max(
         layer.scratch_space_fixed(max_input_len=max_total_tokens, max_batch_size=1)