From 5e1c8c81288d11de9991f216ef9dea63d4fac047 Mon Sep 17 00:00:00 2001 From: pandyamarut Date: Wed, 28 Aug 2024 22:46:45 -0700 Subject: [PATCH 1/2] update vllm version 0.5.5 Signed-off-by: pandyamarut --- Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Dockerfile b/Dockerfile index 0029433..7b1e253 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==0.5.4 && \ +RUN python3 -m pip install vllm==0.5.5 && \ python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3 # Setup for Option 2: Building the Image with the Model included From 3293245c81950274d67e8549df034d2e6d692511 Mon Sep 17 00:00:00 2001 From: pandyamarut Date: Wed, 28 Aug 2024 23:28:39 -0700 Subject: [PATCH 2/2] update tags Signed-off-by: pandyamarut --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 6f604f1..635813a 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 `v1.2.0` with vLLM `0.5.4` now available under `stable` tags +### 2. Worker vLLM `v1.3.0` with vLLM `0.5.4` now available under `stable` tags -Update v1.2.0 is now available, use the image tag `runpod/worker-v1-vllm:v1.2.0stable-cuda12.1.0`. +Update v1.3.0 is now available, use the image tag `runpod/worker-v1-vllm:v1.3.0stable-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!