Unverified Commit d684094b authored by Xuehai Pan's avatar Xuehai Pan Committed by GitHub
Browse files

[Lint] Prefer American English spelling (#1022)


Co-authored-by: default avatarLeiWang1999 <leiwang1999@outlook.com>
parent 7a5077e4
......@@ -28,6 +28,9 @@ repos:
- id: check-ast
fail_fast: true
- id: debug-statements
- id: file-contents-sorter
args: [--ignore-case]
files: ^docs/spelling_wordlist\.txt$
- repo: https://github.com/pre-commit/mirrors-clang-format
rev: v15.0.7 # sync with requirements-lint.txt
hooks:
......
......@@ -242,6 +242,6 @@ Welcome to join our Discord community for discussions, support, and collaboratio
[![Join our Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?logo=discord&style=for-the-badge)](https://discord.gg/TUrHyJnKPG)
## Acknowledgements
## Acknowledgments
We would like to express our gratitude to the [TVM](https://github.com/apache/tvm) community for their invaluable contributions. The initial version of this project was mainly developed by [LeiWang1999](https://github.com/LeiWang1999), [chengyupku](https://github.com/chengyupku) and [nox-410](https://github.com/nox-410) with supervision from Prof. [Zhi Yang](https://yangzhihome.github.io) at Peking University. Part of this work was carried out during an internship at Microsoft Research, where Dr. Lingxiao Ma, Dr. Yuqing Xia, Dr. Jilong Xue, and Dr. Fan Yang offered valuable advice and support. We deeply appreciate their mentorship and contributions.
......@@ -4,7 +4,7 @@
## Why Fences Are Needed
Hopper separates memory instructions into generic and asynchronous proxy paths. When an asynchronous instruction (for example, `cp.async` or `tma.load`) issues after generic traffic (like `ldmatrix` or plain buffer stores), the hardware requires a `fence.proxy.async` to guarantee ordering. Missing fences can lead to race conditions or undefined behaviour.
Hopper separates memory instructions into generic and asynchronous proxy paths. When an asynchronous instruction (for example, `cp.async` or `tma.load`) issues after generic traffic (like `ldmatrix` or plain buffer stores), the hardware requires a `fence.proxy.async` to guarantee ordering. Missing fences can lead to race conditions or undefined behavior.
## What the Pass Does
......
cancelled
hsa
ist
LOD
nd
NotIn
offen
te
......@@ -1718,11 +1718,11 @@ class BitnetForQuestionAnswering(BitnetPreTrainedModel):
) -> Union[Tuple, QuestionAnsweringModelOutput]:
r"""
start_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the start of the labelled span for computing the token classification loss.
Labels for position (index) of the start of the labeled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
end_positions (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
Labels for position (index) of the end of the labelled span for computing the token classification loss.
Labels for position (index) of the end of the labeled span for computing the token classification loss.
Positions are clamped to the length of the sequence (`sequence_length`). Position outside of the sequence
are not taken into account for computing the loss.
"""
......
......@@ -170,9 +170,9 @@ class BitnetTokenizer(PreTrainedTokenizer):
if legacy is None:
logger.warning_once(
f"You are using the default legacy behaviour of the {self.__class__}. This is"
f"You are using the default legacy behavior of the {self.__class__}. This is"
" expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you."
" If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it"
" If you want to use the new behavior, set `legacy=False`. This should only be set if you understand what it"
" means, and thoroughly read the reason why this was added as explained in"
" https://github.com/huggingface/transformers/pull/24565")
legacy = True
......@@ -215,7 +215,7 @@ class BitnetTokenizer(PreTrainedTokenizer):
with open(self.vocab_file, "rb") as f:
sp_model = f.read()
model_pb2 = import_protobuf(
f"The new behaviour of {self.__class__.__name__} (with `self.legacy = False`)")
f"The new behavior of {self.__class__.__name__} (with `self.legacy = False`)")
model = model_pb2.ModelProto.FromString(sp_model)
normalizer_spec = model_pb2.NormalizerSpec()
normalizer_spec.add_dummy_prefix = False
......
......@@ -47,5 +47,6 @@ Notably, TileLang achieves performance parity with hand-optimized assembly kerne
- Improve compute-to-memory access ratios
- Enhance parallelism through dimension-wise task distribution
## Acknowledgement
## Acknowledgment
We would like to express our sincere gratitude to the AMD ROCm and Composable Kernel team for their outstanding contributions. We have learned a great deal from the ROCm software stack.
......@@ -10,5 +10,6 @@
The [chunk_delta_h](common/chunk_delta_h.py) implements the most critical forward kernel of GDN. It's a good start to understand the GDN logic and the TileLang optimization.
## Acknowledgements
## Acknowledgments
This kernel was developed by Yu Cheng and Zhengju Tang following in-depth discussions with Xiaomi's LLM-Core Team (MiMo).
......@@ -81,7 +81,8 @@ column_limit = 100
indent_width = 4
[tool.codespell]
ignore-words-list = "nd, te, ist, LOD, offen, NotIn, HSA"
builtin = "clear,rare,en-GB_to_en-US"
ignore-words = "docs/spelling_wordlist.txt"
skip = [
"build",
"3rdparty",
......
"""TileLang-specific runtime overrides.
Importing this package registers custom handlers that extend or override
behaviour from upstream TVMScript for TileLang semantics.
behavior from upstream TVMScript for TileLang semantics.
"""
# Register parser overrides upon import.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment