add uv to fix vllm transformers install (#59)

* add uv to fix vllm transformers install

Signed-off-by: JaredforReal <w13431838023@gmail.com>

* add comments

Signed-off-by: JaredforReal <w13431838023@gmail.com>

* uv install

Signed-off-by: JaredforReal <w13431838023@gmail.com>

---------

Signed-off-by: JaredforReal <w13431838023@gmail.com>

Author: JaredforReal

README.md

@@ -35,13 +35,17 @@ We provide an SDK for using GLM-OCR more efficiently and conveniently.
 
 ### Install SDK
 
+> [UV Installation](https://docs.astral.sh/uv/getting-started/installation/)
+
 ```bash
 # Install from source
 git clone https://github.com/zai-org/glm-ocr.git
-cd glm-ocr && pip install -e .
+cd glm-ocr
+uv venv --python 3.12 --seed && source .venv/bin/activate
+uv pip install -e .
 
 # Install transformers from source
-pip install git+https://github.com/huggingface/transformers.git
+uv pip install git+https://github.com/huggingface/transformers.git
 ```
 
 ### Model Deployment
@@ -83,15 +87,16 @@ Deploy the GLM-OCR model locally for full control. The SDK provides the complete
 Install vLLM:
 
 ```bash
-pip install -U vllm --extra-index-url https://wheels.vllm.ai/nightly
+uv pip install -U vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
 # Or use Docker
 docker pull vllm/vllm-openai:nightly
 ```
 
 Launch the service:
 
 ```bash
-pip install git+https://github.com/huggingface/transformers.git
+# In docker container, uv may not be need for transformers install
+uv pip install git+https://github.com/huggingface/transformers.git
 
 # Run with MTP for better performance
 vllm serve zai-org/GLM-OCR --allowed-local-media-path / --port 8080 --speculative-config '{"method": "mtp", "num_speculative_tokens": 1}'
@@ -104,13 +109,14 @@ Install SGLang:
 ```bash
 docker pull lmsysorg/sglang:dev
 # Or build from source
-pip install git+https://github.com/sgl-project/sglang.git#subdirectory=python
+uv pip install git+https://github.com/sgl-project/sglang.git#subdirectory=python
 ```
 
 Launch the service:
 
 ```bash
-pip install git+https://github.com/huggingface/transformers.git
+# In docker container, uv may not be need for transformers install
+uv pip install git+https://github.com/huggingface/transformers.git
 
 # Run with MTP for better performance
 python -m sglang.launch_server --model zai-org/GLM-OCR --port 8080 --speculative-algorithm NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

README_zh.md

@@ -35,15 +35,17 @@ GLM-OCR 是一款面向复杂文档理解的多模态 OCR 模型，基于 GLM-V
 
 ### 安装 SDK
 
-```bash
-pip install glmocr
+> [UV 安装](https://docs.astral.sh/uv/getting-started/installation/)
 
-# 或从源码安装
+```bash
+# 从源码安装
 git clone https://github.com/zai-org/glm-ocr.git
-cd glm-ocr && pip install -e .
+cd glm-ocr
+uv venv --python 3.12 --seed && source .venv/bin/activate
+uv pip install -e .
 
 # 从源码安装 transformers
-pip install git+https://github.com/huggingface/transformers.git
+uv pip install git+https://github.com/huggingface/transformers.git
 ```
 
 ### 模型服务部署
@@ -85,15 +87,16 @@ API 文档：https://docs.bigmodel.cn/cn/guide/models/vlm/glm-ocr
 安装 vLLM：
 
 ```bash
-pip install -U vllm --extra-index-url https://wheels.vllm.ai/nightly
+uv pip install -U vllm --torch-backend=auto --extra-index-url https://wheels.vllm.ai/nightly
 # 或使用 Docker
 docker pull vllm/vllm-openai:nightly
 ```
 
 启动服务：
 
 ```bash
-pip install git+https://github.com/huggingface/transformers.git
+# 在 docker 容器中，或许不在需要 uv 来安装transformers
+uv pip install git+https://github.com/huggingface/transformers.git
 vllm serve zai-org/GLM-OCR --allowed-local-media-path / --port 8080
 
 # 打开MTP，获得更好的推理性能
@@ -107,13 +110,14 @@ vllm serve zai-org/GLM-OCR --allowed-local-media-path / --port 8080 --speculativ
 ```bash
 docker pull lmsysorg/sglang:dev
 # 或从源码安装
-pip install git+https://github.com/sgl-project/sglang.git#subdirectory=python
+uv pip install git+https://github.com/sgl-project/sglang.git#subdirectory=python
 ```
 
 启动服务：
 
 ```bash
-pip install git+https://github.com/huggingface/transformers.git
+# 在 docker 容器中，或许不在需要 uv 来安装transformers
+uv pip install git+https://github.com/huggingface/transformers.git
 python -m sglang.launch_server --model zai-org/GLM-OCR --port 8080
 
 # 打开MTP，获得更好的推理性能