1 Star 0 Fork 0

zhangboyue/FlagGems

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README
Apache-2.0

English

img_v3_02gp_8115f603-cc89-4e96-ae9d-f01b4fef796g

介绍

FlagGems是一个使用OpenAI推出的Triton编程语言实现的高性能通用算子库,旨在为大语言模型提供一系列可应用于PyTorch框架的算子,加速模型的推理与训练。

FlagGems通过对PyTorch的后端aten算子进行覆盖重写,实现算子库的无缝替换,使用户能够在不修改模型代码的情况下平稳地切换到triton算子库。FlagGems不会影响aten后端的正常使用,并且会带来良好的性能提升。Triton语言为算子库提供了更好的可读性和易用性,同时保持了不逊于CUDA的算子性能,因此开发者只需付出较低的学习成本,即可参与FlagGems的算子开发与建设。

我们为FlagGems创建了微信群。扫描二维码即可加入群聊!第一时间了解我们的动态和信息和新版本发布,或者有任何问题或想法,请立即加入我们!

bge_wechat_group

特性

自动代码生成

在FlagGems中,我们提供了一套自动代码生成的机制,开发者可以使用它来便捷地生成pointwise类型的单算子与融合算子。自动代码生成可以处理常规的对位计算、非张量参数、指定输出类型等多种需求。

常规对位计算

在对位算子函数前装饰pointwise_dynamic,可以节省张量寻址、张量读写、并行分块、张量广播、动态维度、非连续存储等的手动处理。例如以下代码,开发者只需简单描述计算逻辑,即可生成灵活高效的Triton核函数与包装代码。

@pointwise_dynamic(promotion_methods=[(0, "COMPLEX_TO_FLOAT")])
@triton.jit
def abs_func(x):
    return tl.abs(x)

非张量参数

在默认情况下,pointwise_dynamic将所有参数均处理为张量,而通过向参数is_tensor传递布尔值列表,开发者可以指定哪些参数是张量,哪些参数非张量。此外,开发者还可以传入dtypes说明非张量参数的数据类型,但这不是必要的。例如以下代码,将alpha参数定义为非张量的浮点数,而xy参数定义为张量。

@pointwise_dynamic(
    is_tensor=[True, True, False],
    dtypes=[None, None, float],
    promotion_methods=[(0,"DEFAULT")]
)
@triton.jit
def add_func(x, y, alpha):
    return x + y * alpha

输出数据类型

此外,开发者必须传入 promotion_methods 来说明该 Op 在进行计算时应该如何进行类型提升以获得正确的输出类型

@pointwise_dynamic(promotion_methods=[(0, "ALWAYS_BOOL")])
@triton.jit
def ge(x, y):
    return x > y

promotion_methods 通过传入 int 来表示需要进行类型提升的参数位置, 通过传入 str 来表示类型提升的方式, str 对于以下枚举类型

class ELEMENTWISE_TYPE_PROMOTION_KIND(Enum):
    DEFAULT = (0,)
    NO_OPMATH = (1,)
    INT_TO_FLOAT = (2,)
    ALWAYS_BOOL = (3,)
    COMPLEX_TO_FLOAT = (4,)
    BOOL_TO_LONG = (5,)

举例:

  • DEFAULT :add
  • NO_OPMATH : where, nextafter, cat
  • INT_TO_FLOAT :sin
  • ALWAYS_BOOL :eq
  • COMPLEX_TO_FLOAT :abs
  • BOOL_TO_LONG :pow

更新日志

v1.0

  • 支持BLAS类算子:addmm, bmm, mm
  • 支持pointwise类算子:abs, add, div, dropout, exp, gelu, mul, pow, reciprocal, relu, rsqrt, silu, sub, triu
  • 支持reduction类算子:cumsum, layernorm, mean, softmax

v2.0

  • 支持BLAS类算子: mv, outer
  • 支持pointwise类算子: bitwise_and, bitwise_not, bitwise_or, cos, clamp, eq, ge, gt, isinf, isnan, le, lt, ne, neg, or, sin, tanh, sigmoid
  • 支持reduction类算子: all, any, amax, argmax, max, min, prod, sum, var_mean, vector_norm, cross_entropy_loss, group_norm, log_softmax, rms_norm
  • 支持融合算子: skip_rms_norm, skip_layer_norm, gelu_and_mul, silu_and_mul, apply_rotary_position_embedding

v2.1

  • 支持Tensor类算子:where, arange, repeat, masked_fill, tile, unique, index_select, masked_select, ones, ones_like, zeros, zeros_like, full, full_like, flip, pad
  • 支持神经网络类算子:embedding
  • 支持基础数学算子:allclose, isclose, isfinite, floor_divide, trunc_divide, maximum, minimum
  • 支持分布类算子:normal, uniform_, exponential_, multinomial, nonzero, topk, rand, randn, rand_like, randn_like
  • 支持科学计算算子:erf, resolve_conj, resolve_neg

快速入门

依赖

  1. Triton >= 2.2.0
  2. PyTorch >= 2.2.0
  3. Transformers >= 4.40.2

安装

git clone https://github.com/FlagOpen/FlagGems.git
cd FlagGems
pip install .

使用

导入

  1. 在进程中永久启用

    import flag_gems
    flag_gems.enable()
    
  2. 暂时启用

    import flag_gems
    with flag_gems.use_gems():
        pass
    
  3. 示例

    import torch
    import flag_gems
    
    M, N, K = 1024, 1024, 1024
    A = torch.randn((M, K), dtype=torch.float16, device="cuda")
    B = torch.randn((K, N), dtype=torch.float16, device="cuda")
    with flag_gems.use_gems():
        C = torch.mm(A, B)
    

执行

  1. 算子正确性测试

    • 在CUDA上运行参考实现
      cd tests
      pytest test_xx_ops.py
      
    • 在CPU上运行参考实现
      cd tests
      pytest test_xx_ops.py --ref cpu
      
  2. 模型正确性测试

    cd examples
    pytest model_xx_test.py
    
  3. 算子性能测试

    • 测试CUDA性能
      cd benchmark
      pytest test_xx_perf.py -s
      
    • 测试端到端性能
      cd benchmark
      pytest test_xx_perf.py -s --mode cpu
      
  4. 运行时打印日志信息

    pytest program.py --log-cli-level debug
    

    测试性能时不建议打开。

支持算子

算子将按照文档OperatorList.md的顺序逐步实现。

支持模型

  • Bert-base-uncased
  • Llama-2-7b
  • Llava-1.5-7b

支持平台

Platform float16 float32 bfloat16
Nvidia A100

性能表现

FlagGems相比Torch Eager模式下ATen算子库的加速比如下图所示。其中,每个算子的加速比综合了多个形状测例的数据,代表该算子的整体性能。

算子加速比

贡献代码

欢迎大家参与FlagGems的算子开发并贡献代码,详情请参考CONTRIBUTING.md

联系我们

如有疑问,请提交issue,或发送邮件至flaggems@baai.ac.cn

证书

本项目基于Apache 2.0

Copyright © 2024 BAAI. All rights reserved. Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document. "Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License. "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License. "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types. "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below). "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof. "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution." "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work. 2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form. 3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed. 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions: (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and (b) You must cause any modified files to carry prominent notices stating that You changed the files; and (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License. 5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions. 6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file. 7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License. 8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages. 9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability. END OF TERMS AND CONDITIONS

简介

暂无描述 展开 收起
Python 等 2 种语言
Apache-2.0
取消

发行版

暂无发行版

贡献者

全部

近期动态

不能加载更多了
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/zhangboyue/FlagGems.git
git@gitee.com:zhangboyue/FlagGems.git
zhangboyue
FlagGems
FlagGems
master

搜索帮助