patrickvonplaten commited on
Commit
3c88f07
·
verified ·
1 Parent(s): b015fb4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -70,10 +70,13 @@ For a production-ready instruction model please use [Mistral-Small-3.1-24B-Instr
70
 
71
  **_Installation_**
72
 
73
- Make sure you install [`vLLM nightly`](https://github.com/vllm-project/vllm/):
 
 
 
74
 
75
  ```
76
- pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly --upgrade
77
  ```
78
 
79
  Doing so should automatically install [`mistral_common >= 1.5.4`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.4).
@@ -83,7 +86,7 @@ To check:
83
  python -c "import mistral_common; print(mistral_common.__version__)"
84
  ```
85
 
86
- You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39) followed by a nightly install of vllm as shown above.
87
 
88
  **_Example_**
89
 
 
70
 
71
  **_Installation_**
72
 
73
+ We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
74
+ to implement production-ready inference pipelines.
75
+
76
+ Make sure you install [`vLLM >= 0.8.0`](https://github.com/vllm-project/vllm/releases/tag/v0.8.0):
77
 
78
  ```
79
+ pip install vllm --ugrade
80
  ```
81
 
82
  Doing so should automatically install [`mistral_common >= 1.5.4`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.4).
 
86
  python -c "import mistral_common; print(mistral_common.__version__)"
87
  ```
88
 
89
+ You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
90
 
91
  **_Example_**
92