haijunlv unsubscribe commited on
Commit
32ab132
·
verified ·
1 Parent(s): 8955cb2

Update the installation of vllm in readme (#13)

Browse files

- Update the installation of vllm in readme (cafee21663b48f5b86a765abc98b683302bc5f1f)


Co-authored-by: lmdeploy <[email protected]>

Files changed (1) hide show
  1. README.md +11 -30
README.md CHANGED
@@ -205,15 +205,10 @@ for chunk in stream:
205
 
206
  #### vLLM inference
207
 
208
- We are still working on merging the PR(https://github.com/vllm-project/vllm/pull/12037) into vLLM. In the meantime, please use the following PR link to install it manually.
209
 
210
  ```python
211
- git clone -b support-internlm3 https://github.com/RunningLeon/vllm.git
212
- # and then follow https://docs.vllm.ai/en/latest/getting_started/installation/gpu/index.html#build-wheel-from-source to install
213
- cd vllm
214
- python use_existing_torch.py
215
- pip install -r requirements-build.txt
216
- pip install -e . --no-build-isolatio
217
  ```
218
 
219
  inference code:
@@ -408,14 +403,10 @@ for chunk in stream:
408
 
409
  #### vLLM inference
410
 
411
- We are still working on merging the PR(https://github.com/vllm-project/vllm/pull/12037) into vLLM. In the meantime, please use the following PR link to install it manually.
 
412
  ```python
413
- git clone https://github.com/RunningLeon/vllm.git
414
- # and then follow https://docs.vllm.ai/en/latest/getting_started/installation/gpu/index.html#build-wheel-from-source to install
415
- cd vllm
416
- python use_existing_torch.py
417
- pip install -r requirements-build.txt
418
- pip install -e . --no-build-isolatio
419
  ```
420
 
421
  inference code
@@ -643,15 +634,10 @@ for chunk in stream:
643
 
644
  ##### vLLM 推理
645
 
646
- 我们还在推动PR(https://github.com/vllm-project/vllm/pull/12037) 合入vllm,现在请使用以下PR链接手动安装
647
 
648
- ```python
649
- git clone https://github.com/RunningLeon/vllm.git
650
- # and then follow https://docs.vllm.ai/en/latest/getting_started/installation/gpu/index.html#build-wheel-from-source to install
651
- cd vllm
652
- python use_existing_torch.py
653
- pip install -r requirements-build.txt
654
- pip install -e . --no-build-isolatio
655
  ```
656
 
657
  推理代码
@@ -845,15 +831,10 @@ for chunk in stream:
845
 
846
  ##### vLLM 推理
847
 
848
- 我们还在推动PR(https://github.com/vllm-project/vllm/pull/12037) 合入vllm,现在请使用以下PR链接手动安装
849
 
850
- ```python
851
- git clone https://github.com/RunningLeon/vllm.git
852
- # and then follow https://docs.vllm.ai/en/latest/getting_started/installation/gpu/index.html#build-wheel-from-source to install
853
- cd vllm
854
- python use_existing_torch.py
855
- pip install -r requirements-build.txt
856
- pip install -e . --no-build-isolatio
857
  ```
858
 
859
  推理代码
 
205
 
206
  #### vLLM inference
207
 
208
+ Refer to [installation](https://docs.vllm.ai/en/latest/getting_started/installation/index.html) to install the latest code of vllm
209
 
210
  ```python
211
+ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 
 
 
 
 
212
  ```
213
 
214
  inference code:
 
403
 
404
  #### vLLM inference
405
 
406
+ Refer to [installation](https://docs.vllm.ai/en/latest/getting_started/installation/index.html) to install the latest code of vllm
407
+
408
  ```python
409
+ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 
 
 
 
 
410
  ```
411
 
412
  inference code
 
634
 
635
  ##### vLLM 推理
636
 
637
+ 参考[文档](https://docs.vllm.ai/en/latest/getting_started/installation/index.html) 安装 vllm 最新代码
638
 
639
+ ```bash
640
+ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 
 
 
 
 
641
  ```
642
 
643
  推理代码
 
831
 
832
  ##### vLLM 推理
833
 
834
+ 参考[文档](https://docs.vllm.ai/en/latest/getting_started/installation/index.html) 安装 vllm 最新代码
835
 
836
+ ```bash
837
+ pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly
 
 
 
 
 
838
  ```
839
 
840
  推理代码