From e9f03f822a766f071620457bd977f7987e65b20e Mon Sep 17 00:00:00 2001
From: Nicolas Patry <patry.nicolas@protonmail.com>
Date: Fri, 26 Apr 2024 19:19:55 +0200
Subject: [PATCH] Dummy CI run. (#1817)

# What does this PR do?

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- Remove if not applicable -->

Fixes # (issue)


## 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

 -->
---
 .../models/flash_causal_lm.py                       | 13 ++++++++++---
 server/text_generation_server/models/flash_llama.py |  1 +
 server/text_generation_server/models/flash_neox.py  |  1 +
 server/text_generation_server/models/flash_rw.py    |  1 +
 .../models/flash_santacoder.py                      |  1 +
 server/text_generation_server/utils/import_utils.py |  2 ++
 server/text_generation_server/utils/layers.py       |  1 +
 7 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py
index 94518b8f..a6d0204f 100644
--- a/server/text_generation_server/models/flash_causal_lm.py
+++ b/server/text_generation_server/models/flash_causal_lm.py
@@ -33,7 +33,12 @@ from text_generation_server.utils import StoppingCriteria, HeterogeneousNextToke
 from text_generation_server.utils.dist import MEMORY_FRACTION
 
 tracer = trace.get_tracer(__name__)
-from text_generation_server.utils.import_utils import IS_CUDA_SYSTEM, IS_ROCM_SYSTEM, IS_XPU_SYSTEM
+from text_generation_server.utils.import_utils import (
+    IS_CUDA_SYSTEM,
+    IS_ROCM_SYSTEM,
+    IS_XPU_SYSTEM,
+)
+
 
 @dataclass
 class FlashCausalLMBatch(Batch):
@@ -788,14 +793,16 @@ class FlashCausalLM(Model):
 
         if IS_CUDA_SYSTEM or IS_ROCM_SYSTEM:
             total_free_memory, _ = torch.cuda.mem_get_info(self.device)
-            total_gpu_memory = torch.cuda.get_device_properties(self.device).total_memory
+            total_gpu_memory = torch.cuda.get_device_properties(
+                self.device
+            ).total_memory
 
             free_memory = max(
                 0, total_free_memory - (1 - MEMORY_FRACTION) * total_gpu_memory
             )
         elif IS_XPU_SYSTEM:
             total_gpu_memory = torch.xpu.get_device_properties(self.device).total_memory
-            free_memory = int(total_gpu_memory *0.5)
+            free_memory = int(total_gpu_memory * 0.5)
         else:
             raise NotImplementedError("FlashModel is only available on GPU")
 
diff --git a/server/text_generation_server/models/flash_llama.py b/server/text_generation_server/models/flash_llama.py
index f37fc542..609a188d 100644
--- a/server/text_generation_server/models/flash_llama.py
+++ b/server/text_generation_server/models/flash_llama.py
@@ -20,6 +20,7 @@ tracer = trace.get_tracer(__name__)
 
 from text_generation_server.utils.import_utils import IS_XPU_SYSTEM
 
+
 class FlashLlama(FlashCausalLM):
     def __init__(
         self,
diff --git a/server/text_generation_server/models/flash_neox.py b/server/text_generation_server/models/flash_neox.py
index 70c978de..f82e27db 100644
--- a/server/text_generation_server/models/flash_neox.py
+++ b/server/text_generation_server/models/flash_neox.py
@@ -15,6 +15,7 @@ from text_generation_server.utils import (
     Weights,
 )
 from text_generation_server.utils.import_utils import IS_XPU_SYSTEM
+
 tracer = trace.get_tracer(__name__)
 
 
diff --git a/server/text_generation_server/models/flash_rw.py b/server/text_generation_server/models/flash_rw.py
index 6eb25f22..ccf38a0c 100644
--- a/server/text_generation_server/models/flash_rw.py
+++ b/server/text_generation_server/models/flash_rw.py
@@ -16,6 +16,7 @@ from text_generation_server.utils import (
     Weights,
 )
 from text_generation_server.utils.import_utils import IS_XPU_SYSTEM
+
 tracer = trace.get_tracer(__name__)
 
 
diff --git a/server/text_generation_server/models/flash_santacoder.py b/server/text_generation_server/models/flash_santacoder.py
index 6147398a..e66f1bf8 100644
--- a/server/text_generation_server/models/flash_santacoder.py
+++ b/server/text_generation_server/models/flash_santacoder.py
@@ -19,6 +19,7 @@ from text_generation_server.utils import (
 )
 
 from text_generation_server.utils.import_utils import IS_XPU_SYSTEM
+
 tracer = trace.get_tracer(__name__)
 
 
diff --git a/server/text_generation_server/utils/import_utils.py b/server/text_generation_server/utils/import_utils.py
index 7c0d8001..db205f4d 100644
--- a/server/text_generation_server/utils/import_utils.py
+++ b/server/text_generation_server/utils/import_utils.py
@@ -1,5 +1,6 @@
 import torch
 
+
 def is_xpu_available():
     try:
         import intel_extension_for_pytorch
@@ -8,6 +9,7 @@ def is_xpu_available():
 
     return hasattr(torch, "xpu") and torch.xpu.is_available()
 
+
 IS_ROCM_SYSTEM = torch.version.hip is not None
 IS_CUDA_SYSTEM = torch.version.cuda is not None
 IS_XPU_SYSTEM = is_xpu_available()
diff --git a/server/text_generation_server/utils/layers.py b/server/text_generation_server/utils/layers.py
index 638cb0a0..8c46ea49 100644
--- a/server/text_generation_server/utils/layers.py
+++ b/server/text_generation_server/utils/layers.py
@@ -8,6 +8,7 @@ from typing import List, Tuple, Optional
 from loguru import logger
 from functools import lru_cache
 
+# Dummy comment.
 HAS_BITS_AND_BYTES = True
 try:
     import bitsandbytes as bnb