From 06c2bb171574068b82029ba0a40f8f0c8f96c026 Mon Sep 17 00:00:00 2001 From: pandyamarut Date: Mon, 30 Dec 2024 15:20:11 -0800 Subject: [PATCH] upgrade vllm version Signed-off-by: pandyamarut --- Dockerfile | 2 +- README.md | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/Dockerfile b/Dockerfile index 752273b..f5a05cc 100644 --- a/Dockerfile +++ b/Dockerfile @@ -12,7 +12,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \ python3 -m pip install --upgrade -r /requirements.txt # Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer -RUN python3 -m pip install vllm==0.6.4 && \ +RUN python3 -m pip install vllm==0.6.6.post1 && \ python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3 # Setup for Option 2: Building the Image with the Model included diff --git a/README.md b/README.md index 7d49828..82cc1a6 100644 --- a/README.md +++ b/README.md @@ -18,9 +18,9 @@ Deploy OpenAI-Compatible Blazing-Fast LLM Endpoints powered by the [vLLM](https: ### 1. UI for Deploying vLLM Worker on RunPod console: ![Demo of Deploying vLLM Worker on RunPod console with new UI](media/ui_demo.gif) -### 2. Worker vLLM `v1.7.0` with vLLM `0.6.3` now available under `stable` tags +### 2. Worker vLLM `v1.8.0` with vLLM `0.6.6` now available under `stable` tags -Update v1.7.0 is now available, use the image tag `runpod/worker-v1-vllm:v1.7.0stable-cuda12.1.0`. +Update v1.8.0 is now available, use the image tag `runpod/worker-v1-vllm:v1.8.0stable-cuda12.1.0`. ### 3. OpenAI-Compatible [Embedding Worker](https://github.com/runpod-workers/worker-infinity-embedding) Released Deploy your own OpenAI-compatible Serverless Endpoint on RunPod with multiple embedding models and fast inference for RAG and more! @@ -82,7 +82,7 @@ Below is a summary of the available RunPod Worker images, categorized by image s | CUDA Version | Stable Image Tag | Development Image Tag | Note | |--------------|-----------------------------------|-----------------------------------|----------------------------------------------------------------------| -| 12.1.0 | `runpod/worker-v1-vllm:v1.6.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v1.6.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. | +| 12.1.0 | `runpod/worker-v1-vllm:v1.8.0stable-cuda12.1.0` | `runpod/worker-v1-vllm:v1.8.0dev-cuda12.1.0` | When creating an Endpoint, select CUDA Version 12.3, 12.2 and 12.1 in the filter. |