Skip to content

Commit 144349c

Browse files
authored
remove python wqdependencies (#525)
1 parent 346cd58 commit 144349c

File tree

3 files changed

+16
-12
lines changed

3 files changed

+16
-12
lines changed

README.md

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -202,7 +202,13 @@ For more details, please see API document and [examples](examples/README.md).
202202
Firstly, please install the dependencies.
203203
- Python dependencies
204204
```bash
205-
pip install -r requirements.txt
205+
cmake==3.26.1
206+
sentencepiece==0.2.0
207+
torch==2.7.0+cpu
208+
transformers==4.50.0
209+
accelerate==1.5.1
210+
protobuf==5.29.3
211+
tiktoken==0.9.0
206212
```
207213
***PS: Due to the potential compatibility issues between the model file and the `transformers` version, please select the appropriate `transformers` version.***
208214
- oneCCL (For multi ranks)
@@ -446,7 +452,7 @@ and
446452
***A***:This is because the program launched through MPI reads `OMP_NUM_THREADS=1`, which cannot correctly retrieve the appropriate value from the environment. It is necessary to manually set the value of `OMP_NUM_THREADS` based on the actual situation.
447453

448454
- ***Q***: Why do I still encounter errors when converting already supported models?
449-
***A***: Try downgrading `transformer` to an appropriate version, such as the version specified in the `requirements.txt`. This is because different versions of Transformer may change the names of certain variables.
455+
***A***: Try downgrading `transformer` to an appropriate version. This is because different versions of Transformer may change the names of certain variables.
450456

451457
- ***Q***: I encountered an error saying that `mkl.h` could not be found during compilation. What should I do?
452458
***A***: Please check if the `onednn` folder under `3rdparty/` is empty. If it is, delete it and rerun CMake. Additionally, if the `3rdparty/mkl/` folder contains only a `local` directory, move all contents from `mkl/local/*` to `mkl/`.

README_CN.md

Lines changed: 8 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -202,7 +202,13 @@ xFasterTransformer 支持的模型格式与 Huggingface 有所不同,但与 Fa
202202
首先,请安装依赖项。
203203
- Python 依赖项
204204
```bash
205-
pip install -r requirements.txt
205+
cmake==3.26.1
206+
sentencepiece==0.2.0
207+
torch==2.7.0+cpu
208+
transformers==4.50.0
209+
accelerate==1.5.1
210+
protobuf==5.29.3
211+
tiktoken==0.9.0
206212
```
207213
***PS: 由于模型文件和 `transformers`版本之间可能存在兼容性问题,请选择适当的 `transformers`版本。***
208214
- oneCCL (用于多进程)
@@ -449,7 +455,7 @@ and
449455
******:这是因为通过 MPI 启动的程序读取的是 `OMP_NUM_THREADS=1`,无法从环境中正确获取相应的值。有必要根据实际情况手动设置 `OMP_NUM_THREADS` 的值。
450456

451457
- ******: 为什么在转换已支持的模型时仍会遇到错误?
452-
******: 尝试将 `transformer` 降级到合适的版本,如 `requirements.txt` 中指定的版本。这是因为不同版本的 Transformer 可能会更改某些变量的名称。
458+
******: 尝试将 `transformer` 降级到合适的版本。这是因为不同版本的 Transformer 可能会更改某些变量的名称。
453459

454460
- ******:编译时遇到错误,提示找不到 `mkl.h`,我该怎么办?
455461
******:请检查 `3rdparty/` 目录下的 `onednn` 文件夹是否为空。如果为空,请将其删除并重新运行 CMake。此外,如果 `3rdparty/mkl/` 文件夹内仅包含 `local` 目录,请将 `mkl/local/*` 中的所有内容移动到 `mkl/` 目录下。

requirements.txt

Lines changed: 0 additions & 8 deletions
This file was deleted.

0 commit comments

Comments
 (0)